You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by ma...@apache.org on 2026/01/22 04:40:54 UTC

(opennlp) branch opennlp-2.x updated (10a3a372 -> 9ca9639e)

This is an automated email from the ASF dual-hosted git repository.

mawiesne pushed a change to branch opennlp-2.x
in repository https://gitbox.apache.org/repos/asf/opennlp.git


    from 10a3a372 [2.x]: OPENNLP-1795: Move to Apache Parent 37 (#934)
     new 94113f5b OPENNLP-1791: Document the use of ClassPathModelProvider in dev manual (#919)
     new 9ca9639e OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual (#920)

The 2 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.


Summary of changes:
 opennlp-distr/src/main/assembly/bin.xml            |   20 +
 opennlp-docs/pom.xml                               |  193 +-
 opennlp-docs/src/docbkx/chunker.xml                |  169 +-
 opennlp-docs/src/docbkx/cli.xml                    | 8611 ++++++++++----------
 opennlp-docs/src/docbkx/coref.xml                  |   98 +-
 opennlp-docs/src/docbkx/corpora.xml                |  260 +-
 .../{opennlp-docs.css => opennlp-dev-manual.css}   |   64 +-
 opennlp-docs/src/docbkx/doccat.xml                 |  111 +-
 opennlp-docs/src/docbkx/evaltest.xml               |   42 +-
 opennlp-docs/src/docbkx/extension.xml              |    8 +-
 .../images/{opennlp-logo.png => opennlp-cover.png} |  Bin
 opennlp-docs/src/docbkx/introduction.xml           |  137 +-
 opennlp-docs/src/docbkx/langdetect.xml             |   88 +-
 opennlp-docs/src/docbkx/lemmatizer.xml             |  224 +-
 opennlp-docs/src/docbkx/machine-learning.xml       |   36 +-
 opennlp-docs/src/docbkx/model-loading.xml          |  188 +-
 opennlp-docs/src/docbkx/morfologik-addon.xml       |   40 +-
 opennlp-docs/src/docbkx/namefinder.xml             |  197 +-
 opennlp-docs/src/docbkx/opennlp.xml                |   47 +-
 opennlp-docs/src/docbkx/parser.xml                 |  375 +-
 opennlp-docs/src/docbkx/postagger.xml              |   98 +-
 opennlp-docs/src/docbkx/sentdetect.xml             |  261 +-
 opennlp-docs/src/docbkx/tokenizer.xml              |  156 +-
 opennlp-docs/src/docbkx/uima-integration.xml       |   17 +-
 opennlp-docs/src/main/resources/xsl/epub3.xsl      |   45 +
 opennlp-docs/src/main/resources/xsl/pdf.xsl        |   78 +
 26 files changed, 5926 insertions(+), 5637 deletions(-)
 rename opennlp-docs/src/docbkx/css/{opennlp-docs.css => opennlp-dev-manual.css} (74%)
 copy opennlp-docs/src/docbkx/images/{opennlp-logo.png => opennlp-cover.png} (100%)
 create mode 100644 opennlp-docs/src/main/resources/xsl/epub3.xsl
 create mode 100644 opennlp-docs/src/main/resources/xsl/pdf.xsl


(opennlp) 01/02: OPENNLP-1791: Document the use of ClassPathModelProvider in dev manual (#919)

Posted by ma...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

mawiesne pushed a commit to branch opennlp-2.x
in repository https://gitbox.apache.org/repos/asf/opennlp.git

commit 94113f5bdca5719558432ba81558930349aae54c
Author: Martin Wiesner <ma...@users.noreply.github.com>
AuthorDate: Mon Dec 29 14:09:55 2025 +0100

    OPENNLP-1791: Document the use of ClassPathModelProvider in dev manual (#919)
    
    * OPENNLP-1791: Document the use of ClassPathModelProvider in dev manual
    - adds note on JVM argument since J17 and beyond
    - improves formatting of all "Note:" text fragments to better highlight helpful context to the reader
    
    (cherry picked from commit 7b362c843d6925af76fd3d65f5927c0687b9d454)
---
 opennlp-docs/src/docbkx/doccat.xml        |  2 +-
 opennlp-docs/src/docbkx/langdetect.xml    |  4 ++--
 opennlp-docs/src/docbkx/model-loading.xml | 35 ++++++++++++++++++++++++++++++-
 opennlp-docs/src/docbkx/namefinder.xml    |  2 +-
 opennlp-docs/src/docbkx/parser.xml        |  2 +-
 5 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/opennlp-docs/src/docbkx/doccat.xml b/opennlp-docs/src/docbkx/doccat.xml
index 33ac04a2..5c486dd6 100644
--- a/opennlp-docs/src/docbkx/doccat.xml
+++ b/opennlp-docs/src/docbkx/doccat.xml
@@ -126,7 +126,7 @@ GMDecrease Major acquisitions that have a lower gross margin than the existing n
 GMIncrease The upward movement of gross margin resulted from amounts pursuant to adjustments \
            to obligations towards dealers .]]>
 			</screen>
-			Note: The line breaks marked with a backslash are just inserted for formatting purposes and must not be
+			<emphasis role="strong">Note</emphasis>: The line breaks marked with a backslash are just inserted for formatting purposes and must not be
 			included in the training data.
 		</para>
 		<section id="tools.doccat.training.tool">
diff --git a/opennlp-docs/src/docbkx/langdetect.xml b/opennlp-docs/src/docbkx/langdetect.xml
index 7e901714..0e510c59 100644
--- a/opennlp-docs/src/docbkx/langdetect.xml
+++ b/opennlp-docs/src/docbkx/langdetect.xml
@@ -141,7 +141,7 @@ lav     Egija Tri-Active procedūru īpaši iesaka izmantot siltākajos gadalaik
 		nedēļu laika Ekonomikas ministrijai, Finanšu ministrijai un Labklājības ministrijai, lai ar vienotu \
 		pozīciju atgrieztos pie jautājuma izskatīšanas.]]>
 			</screen>
-			Note: The line breaks marked with a backslash are just inserted for formatting purposes and must not be
+			<emphasis role="strong">Note</emphasis>: The line breaks marked with a backslash are just inserted for formatting purposes and must not be
 			included in the training data.
 		</para>
 		<section id="tools.langdetect.training.tool">
@@ -153,7 +153,7 @@ lav     Egija Tri-Active procedūru īpaši iesaka izmantot siltākajos gadalaik
 $ bin/opennlp LanguageDetectorTrainer[.leipzig] -model modelFile [-params paramsFile] \
   [-factory factoryName] -data sampleData [-encoding charsetName]]]>
 				</screen>
-				Note: To customize the language detector, extend the class opennlp.tools.langdetect.LanguageDetectorFactory
+				<emphasis role="strong">Note</emphasis>: To customize the language detector, extend the class opennlp.tools.langdetect.LanguageDetectorFactory
 				add it to the classpath and pass it in the -factory argument.
 			</para>
 		</section>
diff --git a/opennlp-docs/src/docbkx/model-loading.xml b/opennlp-docs/src/docbkx/model-loading.xml
index aec161cd..e901abf7 100644
--- a/opennlp-docs/src/docbkx/model-loading.xml
+++ b/opennlp-docs/src/docbkx/model-loading.xml
@@ -96,6 +96,39 @@ for(ClassPathModelEntry entry : models) {
             </programlisting>
 
         </para>
+        <para>
+          Moreover, certain OpenNLP models can be obtained via a
+          <emphasis>ClassPathModelProvider</emphasis>, such as OpenNLP's
+          built-in <emphasis>DefaultClassPathModelProvider</emphasis> class.
+          It allows direct use of models available under a certain locale, given
+          that those are present in the classpath and can be loaded.
+
+          <programlisting language="java">
+            <![CDATA[
+final ClassPathModelProvider provider = new DefaultClassPathModelProvider(finder, loader);
+// Here: SentenceModel, other model types accordingly
+final SentenceModel sm = provider.load("en", opennlp.tools.models.ModelType.SENTENCE_DETECTOR, SentenceModel.class);
+if(sm != null) {
+  // do something with the (sentence) model
+}]]>
+          </programlisting>
+
+          In the above example, the finder and loader objects can be created or re-used as shown in the
+          previous code example.
+        </para>
+        <para>
+          <emphasis role="strong">Note</emphasis>:
+          When running on Java 17+, the JVM argument
+          
+          <screen>--add-opens java.base/jdk.internal.loader=ALL-UNNAMED</screen>
+
+          may be required. Without this parameter, OpenNLP uses the JVM bootstrap classpath to locate models
+          rather than the UCP class loader.
+
+          For more advanced or non-standard class loading scenarios, using ClassGraph and implementing a
+          custom provider may cover additional cases beyond the default UCP class loader or
+          JVM bootstrap class path behavior.
+        </para>
 	</section>
 
 
@@ -106,7 +139,7 @@ for(ClassPathModelEntry entry : models) {
             we recommend that you have a look at our setup in the <ulink url="https://github.com/apache/opennlp-models">OpenNLP Models
             repository</ulink>. We recommend to bundle one model per JAR file.
 
-            Make sure you add a <emphasis>model.properties</emphasis> file with the following content
+            Make sure you add a <emphasis>model.properties</emphasis> file with the following content:
 
        <programlisting language="java">
                 <![CDATA[
diff --git a/opennlp-docs/src/docbkx/namefinder.xml b/opennlp-docs/src/docbkx/namefinder.xml
index cdf77d3f..284a4a31 100644
--- a/opennlp-docs/src/docbkx/namefinder.xml
+++ b/opennlp-docs/src/docbkx/namefinder.xml
@@ -506,7 +506,7 @@ Precision: 0.8005071889818507
 Recall: 0.7450581122145297
 F-Measure: 0.7717879983140168]]>
          </screen>
-			 Note: The command line interface does not support cross evaluation in the current version.
+			 <emphasis role="strong">Note</emphasis>: The command line interface does not support cross evaluation in the current version.
 		</para>
 		</section>
 		<section id="tools.namefind.eval.api">
diff --git a/opennlp-docs/src/docbkx/parser.xml b/opennlp-docs/src/docbkx/parser.xml
index 2dc1ecd6..468a3ea8 100644
--- a/opennlp-docs/src/docbkx/parser.xml
+++ b/opennlp-docs/src/docbkx/parser.xml
@@ -200,7 +200,7 @@ $ opennlp ParserTrainer -model en-parser-chunking.bin -parserType CHUNKING \
 		tool replaces the tagger model inside the parser model with a new one. 
 		</para>
 		<para>
-		Note: The original parser model will be overwritten with the new parser model which
+		<emphasis role="strong">Note</emphasis>: The original parser model will be overwritten with the new parser model which
 		contains the replaced tagger model.
         <screen>
 		<![CDATA[


(opennlp) 02/02: OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual (#920)

Posted by ma...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

mawiesne pushed a commit to branch opennlp-2.x
in repository https://gitbox.apache.org/repos/asf/opennlp.git

commit 9ca9639e70dba509cec09b97d18187e9889b6c71
Author: Martin Wiesner <ma...@hs-heilbronn.de>
AuthorDate: Tue Jan 20 15:03:03 2026 +0100

    OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual (#920)
    
    * OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual
    - modernizes xml files of the OpenNLP dev manual to use Docbook dtd in version 5.x
    - adds plugin configuration to produce the PDF as separate outcome
    - adds xsl file for customization of the layout of text in the PDF
    - adds hyphenation support for PDF and epub versions
    - introduces specific profiles for html, pdf, and epub3 targets of the dev manual
    - adds cover entry to opennlp.xml for epub target
    - fixes inconsistencies in dev manual's structure (duplicate ids...)
    - fixes 'informaltable' column counts, mainly in cli.xml
    - fixes missing inlinemediaobject for parsetree1.png image include causing trouble during epub3 generation
    - adds config for pdf and epub file inclusion to bin.xml config in opennlp-distr/assembly
    
    (cherry picked from commit 58d91f05656a363025f6f2801331b2ca3e44daf0)
---
 opennlp-distr/src/main/assembly/bin.xml            |   20 +
 opennlp-docs/pom.xml                               |  193 +-
 opennlp-docs/src/docbkx/chunker.xml                |  169 +-
 opennlp-docs/src/docbkx/cli.xml                    | 8611 ++++++++++----------
 opennlp-docs/src/docbkx/coref.xml                  |   98 +-
 opennlp-docs/src/docbkx/corpora.xml                |  260 +-
 .../{opennlp-docs.css => opennlp-dev-manual.css}   |   64 +-
 opennlp-docs/src/docbkx/doccat.xml                 |  111 +-
 opennlp-docs/src/docbkx/evaltest.xml               |   42 +-
 opennlp-docs/src/docbkx/extension.xml              |    8 +-
 opennlp-docs/src/docbkx/images/opennlp-cover.png   |  Bin 0 -> 30107 bytes
 opennlp-docs/src/docbkx/introduction.xml           |  137 +-
 opennlp-docs/src/docbkx/langdetect.xml             |   88 +-
 opennlp-docs/src/docbkx/lemmatizer.xml             |  224 +-
 opennlp-docs/src/docbkx/machine-learning.xml       |   36 +-
 opennlp-docs/src/docbkx/model-loading.xml          |  199 +-
 opennlp-docs/src/docbkx/morfologik-addon.xml       |   40 +-
 opennlp-docs/src/docbkx/namefinder.xml             |  197 +-
 opennlp-docs/src/docbkx/opennlp.xml                |   47 +-
 opennlp-docs/src/docbkx/parser.xml                 |  375 +-
 opennlp-docs/src/docbkx/postagger.xml              |   98 +-
 opennlp-docs/src/docbkx/sentdetect.xml             |  261 +-
 opennlp-docs/src/docbkx/tokenizer.xml              |  156 +-
 opennlp-docs/src/docbkx/uima-integration.xml       |   17 +-
 opennlp-docs/src/main/resources/xsl/epub3.xsl      |   45 +
 opennlp-docs/src/main/resources/xsl/pdf.xsl        |   78 +
 26 files changed, 5915 insertions(+), 5659 deletions(-)

diff --git a/opennlp-distr/src/main/assembly/bin.xml b/opennlp-distr/src/main/assembly/bin.xml
index 2a7d1498..689dd692 100644
--- a/opennlp-distr/src/main/assembly/bin.xml
+++ b/opennlp-distr/src/main/assembly/bin.xml
@@ -114,6 +114,26 @@
       <outputDirectory>docs/manual</outputDirectory>
     </fileSet>
 
+    <fileSet>
+      <directory>../opennlp-docs/target/docbkx/pdf</directory>
+      <fileMode>644</fileMode>
+      <directoryMode>755</directoryMode>
+      <includes>
+        <include>*.pdf</include>
+      </includes>
+      <outputDirectory>docs</outputDirectory>
+    </fileSet>
+
+    <fileSet>
+      <directory>../opennlp-docs/target/docbkx</directory>
+      <fileMode>644</fileMode>
+      <directoryMode>755</directoryMode>
+      <includes>
+        <include>*.epub</include>
+      </includes>
+      <outputDirectory>docs</outputDirectory>
+    </fileSet>
+
     <fileSet>
       <directory>../opennlp-tools/target/reports/apidocs</directory>
       <fileMode>644</fileMode>
diff --git a/opennlp-docs/pom.xml b/opennlp-docs/pom.xml
index b76fc511..68e469c9 100644
--- a/opennlp-docs/pom.xml
+++ b/opennlp-docs/pom.xml
@@ -30,47 +30,154 @@
   
   <artifactId>opennlp-docs</artifactId>
   <packaging>pom</packaging>
-  <name>Apache OpenNLP Documentation</name>
-  
-  <build>
-    <plugins>
-	<plugin>
-		<groupId>com.agilejava.docbkx</groupId>
-		<artifactId>docbkx-maven-plugin</artifactId>
-		<version>2.0.17</version>
-		<executions>
-          <execution>
-            <goals>
-              <goal>generate-html</goal>
-            </goals>
-            <phase>package</phase>
-          </execution>
-        </executions>
-		<dependencies>
-			<dependency>
-			  <groupId>org.docbook</groupId>
-			  <artifactId>docbook-xml</artifactId>
-			  <version>4.4</version>
-			</dependency>
-       	</dependencies>
-		<configuration>
-			<xincludeSupported>true</xincludeSupported>
-			<includes>opennlp.xml</includes>
-			<htmlStylesheet>css/opennlp-docs.css</htmlStylesheet>
-			<highlightSource>1</highlightSource>
-			<htmlCustomization>${project.basedir}/src/main/resources/xsl/html.xsl</htmlCustomization> 
-			<postProcess>
-				<copy todir="${project.build.directory}/docbkx/html">
-					<fileset dir="${project.basedir}/src/docbkx">
-						<include name="**/*.css" />
-						<include name="**/*.png" />
-						<include name="**/*.gif" />
-						<include name="**/*.jpg" />
-					</fileset>
-				</copy>
-			</postProcess>
-		</configuration>
-	</plugin>
-    </plugins>
-  </build>
+  <name>Apache OpenNLP :: Documentation</name>
+
+	<profiles>
+		<profile>
+			<id>doc-manual-html</id>
+			<activation>
+				<activeByDefault>true</activeByDefault>
+			</activation>
+			<build>
+				<plugins>
+					<plugin>
+						<groupId>com.agilejava.docbkx</groupId>
+						<artifactId>docbkx-maven-plugin</artifactId>
+						<executions>
+							<execution>
+								<id>doc-manual-html</id>
+								<goals>
+									<goal>generate-html</goal>
+								</goals>
+								<phase>package</phase>
+							</execution>
+						</executions>
+						<configuration>
+							<htmlStylesheet>css/opennlp-dev-manual.css</htmlStylesheet>
+							<highlightSource>1</highlightSource>
+							<htmlCustomization>${project.basedir}/src/main/resources/xsl/html.xsl</htmlCustomization>
+							<postProcess>
+								<copy todir="${project.build.directory}/docbkx/html">
+									<fileset dir="${project.basedir}/src/docbkx">
+										<include name="**/*.css" />
+										<include name="**/*.png" />
+										<include name="**/*.gif" />
+										<include name="**/*.jpg" />
+									</fileset>
+								</copy>
+							</postProcess>
+						</configuration>
+					</plugin>
+				</plugins>
+			</build>
+		</profile>
+		<profile>
+			<id>doc-manual-pdf</id>
+			<activation>
+				<activeByDefault>true</activeByDefault>
+			</activation>
+			<build>
+				<plugins>
+					<plugin>
+						<groupId>com.agilejava.docbkx</groupId>
+						<artifactId>docbkx-maven-plugin</artifactId>
+						<executions>
+							<execution>
+								<id>doc-manual-pdf</id>
+								<goals>
+									<goal>generate-pdf</goal>
+								</goals>
+								<phase>package</phase>
+							</execution>
+						</executions>
+						<configuration>
+							<foCustomization>${project.basedir}/src/main/resources/xsl/pdf.xsl</foCustomization>
+							<highlightSource>1</highlightSource>
+							<hyphenate>true</hyphenate>
+							<hyphenateVerbatim>false</hyphenateVerbatim>
+							<showXslMessages>false</showXslMessages>
+						</configuration>
+					</plugin>
+				</plugins>
+			</build>
+		</profile>
+		<profile>
+			<id>doc-manual-epub</id>
+			<activation>
+				<activeByDefault>false</activeByDefault>
+			</activation>
+			<build>
+				<plugins>
+					<plugin>
+						<groupId>com.agilejava.docbkx</groupId>
+						<artifactId>docbkx-maven-plugin</artifactId>
+						<executions>
+							<execution>
+								<id>doc-manual-epub</id>
+								<goals>
+									<goal>generate-epub3</goal>
+								</goals>
+								<phase>package</phase>
+							</execution>
+						</executions>
+						<configuration>
+							<hyphenate>true</hyphenate>
+							<hyphenateVerbatim>false</hyphenateVerbatim>
+							<htmlStylesheet>css/opennlp-dev-manual.css</htmlStylesheet>
+							<epub3Customization>${project.basedir}/src/main/resources/xsl/epub3.xsl</epub3Customization>
+							<chunkQuietly>true</chunkQuietly>
+							<showXslMessages>false</showXslMessages>
+							<preProcess>
+								<copy todir="${project.build.directory}/docbkx/epub3/images">
+									<fileset dir="src/docbkx/images/">
+										<include name="*.png"/>
+									</fileset>
+								</copy>
+								<copy todir="${project.build.directory}/docbkx/epub3/css"
+											file="src/docbkx/css/opennlp-dev-manual.css"/>
+							</preProcess>
+						</configuration>
+					</plugin>
+				</plugins>
+			</build>
+		</profile>
+	</profiles>
+
+	<build>
+		<pluginManagement>
+			<plugins>
+				<plugin>
+					<groupId>com.agilejava.docbkx</groupId>
+					<artifactId>docbkx-maven-plugin</artifactId>
+					<version>2.0.17</version>
+					<dependencies>
+						<dependency>
+							<groupId>net.sf.docbook</groupId>
+							<artifactId>docbook-xml</artifactId>
+							<version>5.0-all</version>
+							<classifier>resources</classifier>
+							<type>zip</type>
+							<scope>runtime</scope>
+						</dependency>
+						<dependency>
+							<groupId>net.sf.xslthl</groupId>
+							<artifactId>xslthl</artifactId>
+							<version>2.0.1</version>
+							<scope>runtime</scope>
+						</dependency>
+						<dependency>
+							<groupId>net.sf.offo</groupId>
+							<artifactId>fop-hyph</artifactId>
+							<version>1.2</version>
+							<scope>runtime</scope>
+						</dependency>
+					</dependencies>
+					<configuration>
+						<xincludeSupported>true</xincludeSupported>
+						<includes>opennlp.xml</includes>
+					</configuration>
+				</plugin>
+			</plugins>
+		</pluginManagement>
+	</build>
 </project>
diff --git a/opennlp-docs/src/docbkx/chunker.xml b/opennlp-docs/src/docbkx/chunker.xml
index 44481992..3cdd0ae4 100644
--- a/opennlp-docs/src/docbkx/chunker.xml
+++ b/opennlp-docs/src/docbkx/chunker.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://cdn.docbook.org/schema/5.0/dtd/docbook.dtd"[
 ]>
 <!--
 Licensed to the Apache Software Foundation (ASF) under one
@@ -21,18 +21,18 @@ specific language governing permissions and limitations
 under the License.
 -->
 
-<chapter id="tools.chunker">
+<chapter xml:id="tools.chunker" xmlns:xlink="http://www.w3.org/1999/xlink">
 
 	<title>Chunker</title>
 
-	<section id="tools.parser.chunking">
+	<section xml:id="tools.parser.chunking">
 		<title>Chunking</title>
 		<para>
 		Text chunking consists of dividing a text in syntactically correlated parts of words,
 		like noun groups, verb groups, but does not specify their internal structure, nor their role in the main sentence. 
 		</para>
 		
-		<section id="tools.parser.chunking.cmdline">
+		<section xml:id="tools.parser.chunking.cmdline">
 		<title>Chunker Tool</title>
 		<para>
 		The easiest way to try out the Chunker is the command line tool. The tool is only intended
@@ -43,14 +43,12 @@ under the License.
 		</para>
 		<para>
         <screen>
-				<![CDATA[
-$ opennlp ChunkerME en-chunker.bin]]>
+<![CDATA[$ opennlp ChunkerME en-chunker.bin]]>
 		</screen>
 		The Chunker now reads a pos tagged sentence per line from stdin.
 		Copy these two sentences to the console: 
 		<screen>
-				<![CDATA[
-Rockwell_NNP International_NNP Corp._NNP 's_POS Tulsa_NNP unit_NN said_VBD it_PRP signed_VBD 
+<![CDATA[Rockwell_NNP International_NNP Corp._NNP 's_POS Tulsa_NNP unit_NN said_VBD it_PRP signed_VBD 
     a_DT tentative_JJ agreement_NN extending_VBG its_PRP$ contract_NN with_IN Boeing_NNP Co._NNP
     to_TO provide_VB structural_JJ parts_NNS for_IN Boeing_NNP 's_POS 747_CD jetliners_NNS ._.
 Rockwell_NNP said_VBD the_DT agreement_NN calls_VBZ for_IN it_PRP to_TO supply_VB 200_CD
@@ -58,8 +56,7 @@ Rockwell_NNP said_VBD the_DT agreement_NN calls_VBZ for_IN it_PRP to_TO supply_V
 		</screen>
 		The Chunker will now echo the sentences grouped tokens to the console:
 				<screen>
-				<![CDATA[
-[NP Rockwell_NNP International_NNP Corp._NNP ] [NP 's_POS Tulsa_NNP unit_NN ] [VP said_VBD ]
+<![CDATA[[NP Rockwell_NNP International_NNP Corp._NNP ] [NP 's_POS Tulsa_NNP unit_NN ] [VP said_VBD ]
     [NP it_PRP ] [VP signed_VBD ] [NP a_DT tentative_JJ agreement_NN ] [VP extending_VBG ]
     [NP its_PRP$ contract_NN ] [PP with_IN ] [NP Boeing_NNP Co._NNP ] [VP to_TO provide_VB ]
     [NP structural_JJ parts_NNS ] [PP for_IN ] [NP Boeing_NNP ] [NP 's_POS 747_CD jetliners_NNS ] ._.
@@ -67,18 +64,20 @@ Rockwell_NNP said_VBD the_DT agreement_NN calls_VBZ for_IN it_PRP to_TO supply_V
     [NP it_PRP ] [VP to_TO supply_VB ] [NP 200_CD additional_JJ so-called_JJ shipsets_NNS ]
     [PP for_IN ] [NP the_DT planes_NNS ] ._.]]>
 		</screen>
-		The tag set used by the English pos model is the <ulink url="https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html">Penn Treebank tag set</ulink>.
+		The tag set used by the English pos model is the
+		<link xlink:href="https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html">
+			Penn Treebank tag set
+		</link>.
 		</para>
 		</section>
-		<section id="tools.parser.chunking.api">
+		<section xml:id="tools.parser.chunking.api">
 		<title>Chunking API</title>
 		<para>
-		    The Chunker can be embedded into an application via its API.
+			The Chunker can be embedded into an application via its API.
 			First the chunker model must be loaded into memory from disk or another source.
 			In the sample below it is loaded from disk.
 			<programlisting language="java">
-				<![CDATA[
-InputStream modelIn = null;
+<![CDATA[InputStream modelIn = null;
 ChunkerModel model = null;
 
 try (modelIn = new FileInputStream("en-chunker.bin")){
@@ -87,8 +86,7 @@ try (modelIn = new FileInputStream("en-chunker.bin")){
 			</programlisting>
 			After the model is loaded a Chunker can be instantiated.
 			<programlisting language="java">
-				<![CDATA[
-ChunkerME chunker = new ChunkerME(model);]]>
+<![CDATA[ChunkerME chunker = new ChunkerME(model);]]>
 			</programlisting>
 			The Chunker instance is now ready to tag data. It expects a tokenized sentence
 			as input, which is represented as a String array, each String object in the array
@@ -97,8 +95,7 @@ ChunkerME chunker = new ChunkerME(model);]]>
 	   <para>
 	   The following code shows how to determine the most likely chunk tag sequence for a sentence.
 	   	<programlisting language="java">
-		  <![CDATA[
-String[] sent = new String[] { "Rockwell", "International", "Corp.", "'s",
+<![CDATA[String[] sent = new String[] { "Rockwell", "International", "Corp.", "'s",
     "Tulsa", "unit", "said", "it", "signed", "a", "tentative", "agreement",
     "extending", "its", "contract", "with", "Boeing", "Co.", "to",
     "provide", "structural", "parts", "for", "Boeing", "'s", "747",
@@ -115,9 +112,8 @@ String[] tag = chunker.chunk(sent, pos);]]>
 			tag can be found at the same index as the token has in the input array.
 			The confidence scores for the returned tags can be easily retrieved from
 			a ChunkerME with the following method call:
-				   	<programlisting language="java">
-		  <![CDATA[
-double[] probs = chunker.probs();]]>
+			<programlisting language="java">
+<![CDATA[double[] probs = chunker.probs();]]>
 			</programlisting>
 			The call to probs is stateful and will always return the probabilities of the last
 			tagged sentence. The probs method should only be called when the tag method
@@ -129,8 +125,7 @@ double[] probs = chunker.probs();]]>
 			The topKSequences method is capable of returning the top sequences.
 			It can be called in a similar way as chunk.
 			<programlisting language="java">
-		  <![CDATA[
-Sequence[] topSequences = chunk.topKSequences(sent, pos);]]>
+<![CDATA[Sequence[] topSequences = chunk.topKSequences(sent, pos);]]>
 			</programlisting>	
 			Each Sequence object contains one sequence. The sequence can be retrieved
 			via Sequence.getOutcomes() which returns a tags array 
@@ -138,20 +133,20 @@ Sequence[] topSequences = chunk.topKSequences(sent, pos);]]>
 	  		 </para>
 		</section>
 	</section>
-	<section id="tools.chunker.training">
+	<section xml:id="tools.chunker.training">
 		<title>Chunker Training</title>
 		<para>
-		The pre-trained models might not be available for a desired language,
-		can not detect important entities or the performance is not good enough outside the news domain.
+			The pre-trained models might not be available for a desired language,
+			can not detect important entities or the performance is not good enough outside the news domain.
 		</para>
 		<para>
-		These are the typical reason to do custom training of the chunker on a new
+			These are the typical reason to do custom training of the chunker on a new
 	    corpus or on a corpus which is extended by private training data taken from the data which should be analyzed.
 		</para>
 		<para>
 		The training data can be converted to the OpenNLP chunker training format,
-		which is based on <ulink url="https://www.cnts.ua.ac.be/conll2000/chunking">CoNLL2000</ulink>.
-        Other formats may also be available.
+		which is based on <link xlink:href="https://www.cnts.ua.ac.be/conll2000/chunking">CoNLL2000</link>.
+		Other formats may also be available.
 		The training data consist of three columns separated one single space. Each word has been put on a
 		separate line and there is an empty line after each sentence. The first column contains
 		the current word, the second its part-of-speech tag and the third its chunk tag. 
@@ -163,8 +158,7 @@ Sequence[] topSequences = chunk.topKSequences(sent, pos);]]>
 		<para>
 		Sample sentence of the training data: 
 		<screen>
-				<![CDATA[
-He        PRP  B-NP
+<![CDATA[He        PRP  B-NP
 reckons   VBZ  B-VP
 the       DT   B-NP
 current   JJ   I-NP
@@ -181,19 +175,22 @@ in        IN   B-PP
 September NNP  B-NP
 .         .    O]]>
 		</screen>
-		Note that for improved visualization the example above uses tabs instead of a single space as column separator.
+			<note>
+			  <para>
+				For improved visualization the example above uses tabs instead of a single space as column separator.
+				</para>
+			</note>
 		</para>
-		<section id="tools.chunker.training.tool">
+		<section xml:id="tools.chunker.training.tool">
 		<title>Training Tool</title>
 		<para>
 		OpenNLP has a command line tool which is used to train the models available from the
 		model download page on various corpora.
 		</para> 
 		<para>
-		    Usage of the tool:
-            <screen>
-				<![CDATA[
-$ opennlp ChunkerTrainerME
+			Usage of the tool:
+			<screen>
+<![CDATA[$ opennlp ChunkerTrainerME
 Usage: opennlp ChunkerTrainerME[.ad] [-params paramsFile] [-iterations num] [-cutoff num] \
                -model modelFile -lang language -data sampleData [-encoding charsetName]
 
@@ -212,77 +209,70 @@ Arguments description:
                 data to be used, usually a file name.
         -encoding charsetName
                 encoding for reading and writing text, if absent the system default is used.]]>
-		</screen>
-		Its now assumed that the English chunker model should be trained from a file called
-		en-chunker.train which is encoded as UTF-8. The following command will train the
-		name finder and write the model to en-chunker.bin: 
-		<screen>
-		<![CDATA[
-$ opennlp ChunkerTrainerME -model en-chunker.bin -lang en -data en-chunker.train -encoding UTF-8]]>
-		</screen>
-		Additionally its possible to specify the number of iterations, the cutoff and to overwrite
-		all types in the training data with a single type.
-		</para>
+			</screen>
+			Its now assumed that the English chunker model should be trained from a file called
+			en-chunker.train which is encoded as UTF-8. The following command will train the
+			name finder and write the model to en-chunker.bin:
+			<screen>
+<![CDATA[$ opennlp ChunkerTrainerME -model en-chunker.bin -lang en -data en-chunker.train -encoding UTF-8]]>
+			</screen>
+			Additionally its possible to specify the number of iterations, the cutoff and to overwrite
+			all types in the training data with a single type.
+			</para>
 		</section>
-        <section id="tools.chunker.training.api">
+		<section xml:id="tools.chunker.training.api">
 		<title>Training API</title>
-            <para>
-                The Chunker offers an API to train a new chunker model. The following sample code
-                illustrates how to do it:
-                <programlisting language="java">
-                    <![CDATA[
+			<para>
+				The Chunker offers an API to train a new chunker model. The following sample code
+				illustrates how to do it:
+				<programlisting language="java">
+<![CDATA[
 ObjectStream<String> lineStream =
     new PlainTextByLineStream(new MarkableFileInputStreamFactory(new File("en-chunker.train")), StandardCharsets.UTF_8);
 
 ChunkerModel model;
-
 try(ObjectStream<ChunkSample> sampleStream = new ChunkSampleStream(lineStream)) {
-  model = ChunkerME.train("eng", sampleStream,
-       TrainingParameters.defaultParams(), new ChunkerFactory());
+  	model = ChunkerME.train("eng", sampleStream, TrainingParameters.defaultParams(), new ChunkerFactory());
 }
 
 try (OutputStream modelOut = new BufferedOutputStream(new FileOutputStream(modelFile))) {
-  model.serialize(modelOut);
+  	model.serialize(modelOut);
 }]]>
-                </programlisting>
-            </para>
+				</programlisting>
+			</para>
 		</section>
 	</section>
 	
-	<section id="tools.chunker.evaluation">
+	<section xml:id="tools.chunker.evaluation">
 		<title>Chunker Evaluation</title>
 		<para>
 		The built-in evaluation can measure the chunker performance. The performance is either
 		measured on a test dataset or via cross validation. 
 		</para>
-		<section id="tools.chunker.evaluation.tool">
+		<section xml:id="tools.chunker.evaluation.tool">
 		<title>Chunker Evaluation Tool</title>
-		<para>
+			<para>
 		    The following command shows how the tool can be run:
-            <screen>
-				<![CDATA[
-$ opennlp ChunkerEvaluator
+				<screen>
+<![CDATA[$ opennlp ChunkerEvaluator
 Usage: opennlp ChunkerEvaluator[.ad] -model model [-misclassified true|false] \
                [-detailedF true|false] -lang language -data sampleData [-encoding charsetName]]]>
-		</screen>
-		A sample of the command considering you have a data sample named en-chunker.eval
-		and you trained a model called en-chunker.bin:
-            <screen>
-				<![CDATA[
-$ opennlp ChunkerEvaluator -model en-chunker.bin -data en-chunker.eval -encoding UTF-8]]>
-		</screen>
-		and here is a sample output:  
-		<screen>
-		<![CDATA[
-Precision: 0.9255923572240226
+				</screen>
+				A sample of the command considering you have a data sample named en-chunker.eval
+				and you trained a model called en-chunker.bin:
+				<screen>
+<![CDATA[$ opennlp ChunkerEvaluator -model en-chunker.bin -data en-chunker.eval -encoding UTF-8]]>
+				</screen>
+				and here is a sample output:
+				<screen>
+<![CDATA[Precision: 0.9255923572240226
 Recall: 0.9220610430991112
 F-Measure: 0.9238233255623465]]>
-		</screen>
-		You can also use the tool to perform 10-fold cross validation of the Chunker.
-The following command shows how the tool can be run:
+				</screen>
+				You can also use the tool to perform 10-fold cross validation of the Chunker.
+				The following command shows how the tool can be run:
         <screen>
-				<![CDATA[
-$ opennlp ChunkerCrossValidator
+<![CDATA[$ opennlp ChunkerCrossValidator
 Usage: opennlp ChunkerCrossValidator[.ad] [-params paramsFile] [-iterations num] [-cutoff num] \
                [-misclassified true|false] [-folds num] [-detailedF true|false] \
                -lang language -data sampleData [-encoding charsetName]
@@ -306,13 +296,12 @@ Arguments description:
                 data to be used, usually a file name.
         -encoding charsetName
                 encoding for reading and writing text, if absent the system default is used.]]>
-		</screen>
-		It is not necessary to pass a model. The tool will automatically split the data to train and evaluate:
+				</screen>
+				It is not necessary to pass a model. The tool will automatically split the data to train and evaluate:
         <screen>
-            <![CDATA[
-$ opennlp ChunkerCrossValidator -lang pt -data en-chunker.cross -encoding UTF-8]]>
-		</screen>
-		</para>
+<![CDATA[$ opennlp ChunkerCrossValidator -lang pt -data en-chunker.cross -encoding UTF-8]]>
+				</screen>
+			</para>
 		</section>
 	</section>
 </chapter>
diff --git a/opennlp-docs/src/docbkx/cli.xml b/opennlp-docs/src/docbkx/cli.xml
index adc6538d..09b3e521 100644
--- a/opennlp-docs/src/docbkx/cli.xml
+++ b/opennlp-docs/src/docbkx/cli.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://cdn.docbook.org/schema/5.0/dtd/docbook.dtd"[
 ]>
 <!--
 Licensed to the Apache Software Foundation (ASF) under one
@@ -21,4232 +21,4387 @@ specific language governing permissions and limitations
 under the License.
 -->
 
-
-<!-- ## Warning ## this content is autogenerated! Please fix issues in to opennlp-tools/src/main/java/opennlp/tools/cmdline/GenerateManualTool.java 
-   and execute the following command in opennlp-tool folder to update this file: 
-
-      mvn -e -q exec:java "-Dexec.mainClass=opennlp.tools.cmdline.GenerateManualTool" "-Dexec.args=../opennlp-docs/src/docbkx/cli.xml"
--->
-
-<chapter id='tools.cli'>
-
-<title>The Command Line Interface</title>
-
-<para>This section details the available tools and parameters of the Command Line Interface. For an introduction in its usage please refer to <xref linkend='intro.cli'/>.  </para>
-
-<section id='tools.cli.doccat'>
-
-<title>Doccat</title>
-
-<section id='tools.cli.doccat.Doccat'>
-
-<title>Doccat</title>
-
-<para>Learned document categorizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp Doccat model < documents
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.doccat.DoccatTrainer'>
-
-<title>DoccatTrainer</title>
-
-<para>Trainer for the learnable document categorizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp DoccatTrainer[.leipzig] [-factory factoryName] [-featureGenerators fg] [-tokenizer tokenizer] 
-        [-params paramsFile] -lang language -model modelFile -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of DoccatFactory where to get implementation and resources.
-	-featureGenerators fg
-		Comma separated feature generator classes. Bag of words is used if not specified.
-	-tokenizer tokenizer
-		Tokenizer implementation. WhitespaceTokenizer is used if not specified.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.doccat.DoccatEvaluator'>
-
-<title>DoccatEvaluator</title>
-
-<para>Measures the performance of the Doccat model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp DoccatEvaluator[.leipzig] -model model [-misclassified true|false] [-reportOutputFile 
-        outputFile] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.doccat.DoccatCrossValidator'>
-
-<title>DoccatCrossValidator</title>
-
-<para>K-fold cross validator for the learnable Document Categorizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp DoccatCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory factoryName] 
-        [-featureGenerators fg] [-tokenizer tokenizer] [-params paramsFile] -lang language [-reportOutputFile 
-        outputFile] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-factory factoryName
-		A sub-class of DoccatFactory where to get implementation and resources.
-	-featureGenerators fg
-		Comma separated feature generator classes. Bag of words is used if not specified.
-	-tokenizer tokenizer
-		Tokenizer implementation. WhitespaceTokenizer is used if not specified.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.doccat.DoccatConverter'>
-
-<title>DoccatConverter</title>
-
-<para>Converts leipzig data format to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp DoccatConverter help|leipzig [help|options...]
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-</section>
-
-<section id='tools.cli.langdetect'>
-
-<title>Langdetect</title>
-
-<section id='tools.cli.langdetect.LanguageDetector'>
-
-<title>LanguageDetector</title>
-
-<para>Learned language detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LanguageDetector model < documents
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.langdetect.LanguageDetectorTrainer'>
-
-<title>LanguageDetectorTrainer</title>
-
-<para>Trainer for the learnable language detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LanguageDetectorTrainer[.leipzig] -model modelFile [-params paramsFile] [-factory factoryName] 
-        -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model modelFile
-		output model file.
-	-params paramsFile
-		training parameters file.
-	-factory factoryName
-		A sub-class of LanguageDetectorFactory where to get implementation and resources.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>samplesPerLanguage</entry>
-<entry>samplesPerLanguage</entry>
-<entry>No</entry>
-<entry>Number of samples per language</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.langdetect.LanguageDetectorConverter'>
-
-<title>LanguageDetectorConverter</title>
-
-<para>Converts leipzig data format to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LanguageDetectorConverter help|leipzig [help|options...]
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>samplesPerLanguage</entry>
-<entry>samplesPerLanguage</entry>
-<entry>No</entry>
-<entry>Number of samples per language</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.langdetect.LanguageDetectorCrossValidator'>
-
-<title>LanguageDetectorCrossValidator</title>
-
-<para>K-fold cross validator for the learnable Language Detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LanguageDetectorCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory 
-        factoryName] [-params paramsFile] [-reportOutputFile outputFile] -data sampleData [-encoding 
-        charsetName] 
+<chapter xml:id="tools.cli">
+
+  <title>The Command Line Interface</title>
+
+  <para>
+    This section details the available tools and parameters of the Command Line Interface.
+    For an introduction in its usage please refer to <xref linkend="intro.cli"/>.
+  </para>
+
+  <section xml:id="tools.cli.doccat">
+    <title>Doccat</title>
+
+    <section xml:id="tools.cli.doccat.Doccat">
+
+    <title>Doccat</title>
+
+    <para>Learned document categorizer</para>
+
+    <screen>
+<![CDATA[Usage: opennlp Doccat model < documents]]>
+    </screen>
+  </section>
+
+  <section xml:id="tools.cli.doccat.DoccatTrainer">
+
+  <title>DoccatTrainer</title>
+
+  <para>Trainer for the learnable document categorizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp DoccatTrainer[.leipzig] [-factory factoryName] [-featureGenerators fg] [-tokenizer tokenizer]
+          [-params paramsFile] -lang language -model modelFile -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of DoccatFactory where to get implementation and resources.
+    -featureGenerators fg
+      Comma separated feature generator classes. Bag of words is used if not specified.
+    -tokenizer tokenizer
+      Tokenizer implementation. WhitespaceTokenizer is used if not specified.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.doccat.DoccatEvaluator">
+
+  <title>DoccatEvaluator</title>
+
+  <para>Measures the performance of the Doccat model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp DoccatEvaluator[.leipzig] -model model [-misclassified true|false] [-reportOutputFile
+          outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.doccat.DoccatCrossValidator">
+
+  <title>DoccatCrossValidator</title>
+
+  <para>K-fold cross validator for the learnable Document Categorizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp DoccatCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory factoryName]
+          [-featureGenerators fg] [-tokenizer tokenizer] [-params paramsFile] -lang language [-reportOutputFile
+          outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -factory factoryName
+      A sub-class of DoccatFactory where to get implementation and resources.
+    -featureGenerators fg
+      Comma separated feature generator classes. Bag of words is used if not specified.
+    -tokenizer tokenizer
+      Tokenizer implementation. WhitespaceTokenizer is used if not specified.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.doccat.DoccatConverter">
+
+  <title>DoccatConverter</title>
+
+  <para>Converts leipzig data format to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp DoccatConverter help|leipzig [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.langdetect">
+
+  <title>Langdetect</title>
+
+  <section xml:id="tools.cli.langdetect.LanguageDetector">
+
+  <title>LanguageDetector</title>
+
+  <para>Learned language detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LanguageDetector model < documents]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.langdetect.LanguageDetectorTrainer">
+
+  <title>LanguageDetectorTrainer</title>
+
+  <para>Trainer for the learnable language detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LanguageDetectorTrainer[.leipzig] -model modelFile [-params paramsFile] [-factory factoryName]
+          -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model modelFile
+      output model file.
+    -params paramsFile
+      training parameters file.
+    -factory factoryName
+      A sub-class of LanguageDetectorFactory where to get implementation and resources.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>samplesPerLanguage</entry>
+  <entry>samplesPerLanguage</entry>
+  <entry>No</entry>
+  <entry>Number of samples per language</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.langdetect.LanguageDetectorConverter">
+
+  <title>LanguageDetectorConverter</title>
+
+  <para>Converts leipzig data format to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LanguageDetectorConverter help|leipzig [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>samplesPerLanguage</entry>
+  <entry>samplesPerLanguage</entry>
+  <entry>No</entry>
+  <entry>Number of samples per language</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.langdetect.LanguageDetectorCrossValidator">
+
+  <title>LanguageDetectorCrossValidator</title>
+
+  <para>K-fold cross validator for the learnable Language Detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LanguageDetectorCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory
+          factoryName] [-params paramsFile] [-reportOutputFile outputFile] -data sampleData [-encoding
+          charsetName]
+  Arguments description:
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -factory factoryName
+      A sub-class of LanguageDetectorFactory where to get implementation and resources.
+    -params paramsFile
+      training parameters file.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>samplesPerLanguage</entry>
+  <entry>samplesPerLanguage</entry>
+  <entry>No</entry>
+  <entry>Number of samples per language</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.langdetect.LanguageDetectorEvaluator">
+
+  <title>LanguageDetectorEvaluator</title>
+
+  <para>Measures the performance of the Language Detector model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LanguageDetectorEvaluator[.leipzig] -model model [-misclassified true|false]
+          [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>leipzig</entry>
+  <entry>sentencesDir</entry>
+  <entry>sentencesDir</entry>
+  <entry>No</entry>
+  <entry>Dir with Leipzig sentences to be used</entry>
+  </row>
+  <row>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>samplesPerLanguage</entry>
+  <entry>samplesPerLanguage</entry>
+  <entry>No</entry>
+  <entry>Number of samples per language</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.dictionary">
+
+  <title>Dictionary</title>
+
+  <section xml:id="tools.cli.dictionary.DictionaryBuilder">
+
+  <title>DictionaryBuilder</title>
+
+  <para>Builds a new dictionary</para>
+
+  <screen>
+<![CDATA[Usage: opennlp DictionaryBuilder -outputFile out -inputFile in [-encoding charsetName]
+
+  Arguments description:
+    -outputFile out
+      The dictionary file.
+    -inputFile in
+      Plain file with one entry per line
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.tokenizer">
+
+  <title>Tokenizer</title>
+
+  <section xml:id="tools.cli.tokenizer.SimpleTokenizer">
+
+  <title>SimpleTokenizer</title>
+
+  <para>Character class tokenizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp SimpleTokenizer < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.tokenizer.TokenizerME">
+
+  <title>TokenizerME</title>
+
+  <para>Learnable tokenizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenizerME model < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.tokenizer.TokenizerTrainer">
+
+  <title>TokenizerTrainer</title>
+
+  <para>Trainer for the learnable tokenizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenizerTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] [-factory
+          factoryName] [-abbDict path] [-alphaNumOpt isAlphaNumOpt] [-params paramsFile] -lang language -model
+          modelFile -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of TokenizerFactory where to get implementation and resources.
+    -abbDict path
+      abbreviation dictionary in XML format.
+    -alphaNumOpt isAlphaNumOpt
+      Optimization flag to skip alpha numeric tokens for further tokenization
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllu</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.tokenizer.TokenizerMEEvaluator">
+
+  <title>TokenizerMEEvaluator</title>
+
+  <para>Evaluator for the learnable tokenizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenizerMEEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] -model
+          model [-misclassified true|false] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllu</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.tokenizer.TokenizerCrossValidator">
+
+  <title>TokenizerCrossValidator</title>
+
+  <para>K-fold cross validator for the learnable tokenizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenizerCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu]
+          [-misclassified true|false] [-folds num] [-factory factoryName] [-abbDict path] [-alphaNumOpt
+          isAlphaNumOpt] [-params paramsFile] -lang language -data sampleData [-encoding charsetName]
+  Arguments description:
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -factory factoryName
+      A sub-class of TokenizerFactory where to get implementation and resources.
+    -abbDict path
+      abbreviation dictionary in XML format.
+    -alphaNumOpt isAlphaNumOpt
+      Optimization flag to skip alpha numeric tokens for further tokenization
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllu</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.tokenizer.TokenizerConverter">
+
+  <title>TokenizerConverter</title>
+
+  <para>Converts foreign data formats (irishsentencebank,ad,pos,conllx,namefinder,parse,conllu) to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenizerConverter help|irishsentencebank|ad|pos|conllx|namefinder|parse|conllu
+          [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllu</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.tokenizer.DictionaryDetokenizer">
+
+  <title>DictionaryDetokenizer</title>
+
+  <para/>
+
+  <screen>
+<![CDATA[Usage: opennlp DictionaryDetokenizer detokenizerDictionary]]>
+  </screen>
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.sentdetect">
+
+  <title>Sentdetect</title>
+
+  <section xml:id="tools.cli.sentdetect.SentenceDetector">
+
+  <title>SentenceDetector</title>
+
+  <para>Learnable sentence detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp SentenceDetector model < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.sentdetect.SentenceDetectorTrainer">
+
+  <title>SentenceDetectorTrainer</title>
+
+  <para>Trainer for the learnable sentence detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp
+          SentenceDetectorTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
+          [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language -model
+          modelFile -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of SentenceDetectorFactory where to get implementation and resources.
+    -eosChars string
+      EOS characters.
+    -abbDict path
+      abbreviation dictionary in XML format.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>includeTitles</entry>
+  <entry>includeTitles</entry>
+  <entry>Yes</entry>
+  <entry>If true will include sentences marked as headlines.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>moses</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>letsmt</entry>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>Yes</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.sentdetect.SentenceDetectorEvaluator">
+
+  <title>SentenceDetectorEvaluator</title>
+
+  <para>Evaluator for the learnable sentence detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp
+          SentenceDetectorEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
+          -model model [-misclassified true|false] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>includeTitles</entry>
+  <entry>includeTitles</entry>
+  <entry>Yes</entry>
+  <entry>If true will include sentences marked as headlines.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>moses</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>letsmt</entry>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>Yes</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.sentdetect.SentenceDetectorCrossValidator">
+
+  <title>SentenceDetectorCrossValidator</title>
+
+  <para>K-fold cross validator for the learnable sentence detector</para>
+
+  <screen>
+<![CDATA[Usage: opennlp
+          SentenceDetectorCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
+          [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language
+          [-misclassified true|false] [-folds num] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of SentenceDetectorFactory where to get implementation and resources.
+    -eosChars string
+      EOS characters.
+    -abbDict path
+      abbreviation dictionary in XML format.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>includeTitles</entry>
+  <entry>includeTitles</entry>
+  <entry>Yes</entry>
+  <entry>If true will include sentences marked as headlines.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>moses</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>letsmt</entry>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>Yes</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.sentdetect.SentenceDetectorConverter">
+
+  <title>SentenceDetectorConverter</title>
+
+  <para>Converts foreign data formats (irishsentencebank,ad,pos,conllx,namefinder,parse,moses,conllu,letsmt) to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp SentenceDetectorConverter
+          help|irishsentencebank|ad|pos|conllx|namefinder|parse|moses|conllu|letsmt [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='1' valign='middle'>irishsentencebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>includeTitles</entry>
+  <entry>includeTitles</entry>
+  <entry>Yes</entry>
+  <entry>If true will include sentences marked as headlines.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>pos</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>namefinder</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>No</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>moses</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>sentencesPerSample</entry>
+  <entry>No</entry>
+  <entry>Number of sentences per sample</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>letsmt</entry>
+  <entry>detokenizer</entry>
+  <entry>dictionary</entry>
+  <entry>Yes</entry>
+  <entry>Specifies the file with detokenizer dictionary.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.namefind">
+
+  <title>Namefind</title>
+
+  <section xml:id="tools.cli.namefind.TokenNameFinder">
+
+  <title>TokenNameFinder</title>
+
+  <para>Learnable name finder</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenNameFinder model1 model2 ... modelN < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.namefind.TokenNameFinderTrainer">
+
+  <title>TokenNameFinderTrainer</title>
+
+  <para>Trainer for the learnable name finder</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenNameFinderTrainer[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
+          [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile]
+          [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language -model modelFile -data
+          sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of TokenNameFinderFactory
+    -resources resourcesDir
+      The resources directory
+    -type modelType
+      The type of the token name finder model
+    -featuregen featuregenFile
+      The feature generator descriptor file
+    -nameTypes types
+      name types to use for training
+    -sequenceCodec codec
+      sequence codec used to code name spans
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>evalita</entry>
+  <entry>lang</entry>
+  <entry>it</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,gpe</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll03</entry>
+  <entry>lang</entry>
+  <entry>eng|deu</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>bionlp2004</entry>
+  <entry>types</entry>
+  <entry>DNA, protein, cell_type, cell_line, RNA</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll02</entry>
+  <entry>lang</entry>
+  <entry>spa|nld</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>muc6</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='5' valign='middle'>brat</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>ruleBasedTokenizer</entry>
+  <entry>name</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>annotationConfig</entry>
+  <entry>annConfFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>bratDataDir</entry>
+  <entry>bratDataDir</entry>
+  <entry>No</entry>
+  <entry>Location of brat data dir</entry>
+  </row>
+  <row>
+  <entry>recursive</entry>
+  <entry>value</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>sentenceDetectorModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.namefind.TokenNameFinderEvaluator">
+
+  <title>TokenNameFinderEvaluator</title>
+
+  <para>Measures the performance of the NameFinder model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenNameFinderEvaluator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
+          [-nameTypes types] -model model [-misclassified true|false] [-detailedF true|false]
+          [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -nameTypes types
+      name types to use for evaluation
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -detailedF true|false
+      if true (default) will print detailed FMeasure results.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>evalita</entry>
+  <entry>lang</entry>
+  <entry>it</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,gpe</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll03</entry>
+  <entry>lang</entry>
+  <entry>eng|deu</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>bionlp2004</entry>
+  <entry>types</entry>
+  <entry>DNA, protein, cell_type, cell_line, RNA</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll02</entry>
+  <entry>lang</entry>
+  <entry>spa|nld</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>muc6</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='5' valign='middle'>brat</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>ruleBasedTokenizer</entry>
+  <entry>name</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>annotationConfig</entry>
+  <entry>annConfFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>bratDataDir</entry>
+  <entry>bratDataDir</entry>
+  <entry>No</entry>
+  <entry>Location of brat data dir</entry>
+  </row>
+  <row>
+  <entry>recursive</entry>
+  <entry>value</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>sentenceDetectorModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.namefind.TokenNameFinderCrossValidator">
+
+  <title>TokenNameFinderCrossValidator</title>
+
+  <para>K-fold cross validator for the learnable Name Finder</para>
+
+  <screen>
+<![CDATA[Usage: opennlp
+          TokenNameFinderCrossValidator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
+          [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile]
+          [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language [-misclassified
+          true|false] [-folds num] [-detailedF true|false] [-reportOutputFile outputFile] -data sampleData
+          [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of TokenNameFinderFactory
+    -resources resourcesDir
+      The resources directory
+    -type modelType
+      The type of the token name finder model
+    -featuregen featuregenFile
+      The feature generator descriptor file
+    -nameTypes types
+      name types to use for training
+    -sequenceCodec codec
+      sequence codec used to code name spans
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -detailedF true|false
+      if true (default) will print detailed FMeasure results.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>evalita</entry>
+  <entry>lang</entry>
+  <entry>it</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,gpe</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll03</entry>
+  <entry>lang</entry>
+  <entry>eng|deu</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>bionlp2004</entry>
+  <entry>types</entry>
+  <entry>DNA, protein, cell_type, cell_line, RNA</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll02</entry>
+  <entry>lang</entry>
+  <entry>spa|nld</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>muc6</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='5' valign='middle'>brat</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>ruleBasedTokenizer</entry>
+  <entry>name</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>annotationConfig</entry>
+  <entry>annConfFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>bratDataDir</entry>
+  <entry>bratDataDir</entry>
+  <entry>No</entry>
+  <entry>Location of brat data dir</entry>
+  </row>
+  <row>
+  <entry>recursive</entry>
+  <entry>value</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>sentenceDetectorModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.namefind.TokenNameFinderConverter">
+
+  <title>TokenNameFinderConverter</title>
+
+  <para>Converts foreign data formats (evalita,ad,conll03,bionlp2004,conll02,muc6,ontonotes,brat) to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TokenNameFinderConverter help|evalita|ad|conll03|bionlp2004|conll02|muc6|ontonotes|brat
+          [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='3' valign='middle'>evalita</entry>
+  <entry>lang</entry>
+  <entry>it</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,gpe</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>splitHyphenatedTokens</entry>
+  <entry>split</entry>
+  <entry>Yes</entry>
+  <entry>If true all hyphenated tokens will be separated (default true)</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll03</entry>
+  <entry>lang</entry>
+  <entry>eng|deu</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>bionlp2004</entry>
+  <entry>types</entry>
+  <entry>DNA, protein, cell_type, cell_line, RNA</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='3' valign='middle'>conll02</entry>
+  <entry>lang</entry>
+  <entry>spa|nld</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>types</entry>
+  <entry>per,loc,org,misc</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>muc6</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='5' valign='middle'>brat</entry>
+  <entry>tokenizerModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>ruleBasedTokenizer</entry>
+  <entry>name</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>annotationConfig</entry>
+  <entry>annConfFile</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>bratDataDir</entry>
+  <entry>bratDataDir</entry>
+  <entry>No</entry>
+  <entry>Location of brat data dir</entry>
+  </row>
+  <row>
+  <entry>recursive</entry>
+  <entry>value</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry>sentenceDetectorModel</entry>
+  <entry>modelFile</entry>
+  <entry>Yes</entry>
+  <entry></entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.namefind.CensusDictionaryCreator">
+
+  <title>CensusDictionaryCreator</title>
+
+  <para>Converts 1990 US Census names into a dictionary</para>
+
+  <screen>
+<![CDATA[Usage: opennlp CensusDictionaryCreator [-encoding charsetName] [-lang code] -censusData censusDict -dict dict
+
+  Arguments description:
+    -encoding charsetName
+    -lang code
+    -censusData censusDict
+    -dict dict]]>
+  </screen>
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.postag">
+
+  <title>Postag</title>
+
+  <section xml:id="tools.cli.postag.POSTagger">
+
+  <title>POSTagger</title>
+
+  <para>Learnable part of speech tagger</para>
+
+  <screen>
+<![CDATA[Usage: opennlp POSTagger model < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.postag.POSTaggerTrainer">
+
+  <title>POSTaggerTrainer</title>
+
+  <para>Trains a model for the part-of-speech tagger</para>
+
+  <screen>
+<![CDATA[Usage: opennlp POSTaggerTrainer[.ad|.conllx|.parse|.ontonotes|.conllu] [-factory factoryName] [-resources
+          resourcesDir] [-tagDictCutoff tagDictCutoff] [-featuregen featuregenFile] [-dict dictionaryPath]
+          [-params paramsFile] -lang language -model modelFile -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of POSTaggerFactory where to get implementation and resources.
+    -resources resourcesDir
+      The resources directory
+    -tagDictCutoff tagDictCutoff
+      TagDictionary cutoff. If specified will create/expand a mutable TagDictionary
+    -featuregen featuregenFile
+      The feature generator descriptor file
+    -dict dictionaryPath
+      The XML tag dictionary file
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>expandME</entry>
+  <entry>expandME</entry>
+  <entry>Yes</entry>
+  <entry>Expand multiword expressions.</entry>
+  </row>
+  <row>
+  <entry>includeFeatures</entry>
+  <entry>includeFeatures</entry>
+  <entry>Yes</entry>
+  <entry>Combine POS Tags with word features, like number and gender.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>tagset</entry>
+  <entry>tagset</entry>
+  <entry>Yes</entry>
+  <entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.postag.POSTaggerEvaluator">
+
+  <title>POSTaggerEvaluator</title>
+
+  <para>Measures the performance of the POS tagger model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp POSTaggerEvaluator[.ad|.conllx|.parse|.ontonotes|.conllu] -model model [-misclassified
+          true|false] [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>expandME</entry>
+  <entry>expandME</entry>
+  <entry>Yes</entry>
+  <entry>Expand multiword expressions.</entry>
+  </row>
+  <row>
+  <entry>includeFeatures</entry>
+  <entry>includeFeatures</entry>
+  <entry>Yes</entry>
+  <entry>Combine POS Tags with word features, like number and gender.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>tagset</entry>
+  <entry>tagset</entry>
+  <entry>Yes</entry>
+  <entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.postag.POSTaggerCrossValidator">
+
+  <title>POSTaggerCrossValidator</title>
+
+  <para>K-fold cross validator for the learnable POS tagger</para>
+
+  <screen>
+<![CDATA[Usage: opennlp POSTaggerCrossValidator[.ad|.conllx|.parse|.ontonotes|.conllu] [-misclassified true|false]
+          [-folds num] [-factory factoryName] [-resources resourcesDir] [-tagDictCutoff tagDictCutoff]
+          [-featuregen featuregenFile] [-dict dictionaryPath] [-params paramsFile] -lang language
+          [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -factory factoryName
+      A sub-class of POSTaggerFactory where to get implementation and resources.
+    -resources resourcesDir
+      The resources directory
+    -tagDictCutoff tagDictCutoff
+      TagDictionary cutoff. If specified will create/expand a mutable TagDictionary
+    -featuregen featuregenFile
+      The feature generator descriptor file
+    -dict dictionaryPath
+      The XML tag dictionary file
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>expandME</entry>
+  <entry>expandME</entry>
+  <entry>Yes</entry>
+  <entry>Expand multiword expressions.</entry>
+  </row>
+  <row>
+  <entry>includeFeatures</entry>
+  <entry>includeFeatures</entry>
+  <entry>Yes</entry>
+  <entry>Combine POS Tags with word features, like number and gender.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>tagset</entry>
+  <entry>tagset</entry>
+  <entry>Yes</entry>
+  <entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.postag.POSTaggerConverter">
+
+  <title>POSTaggerConverter</title>
+
+  <para>Converts foreign data formats (ad,conllx,parse,ontonotes,conllu) to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp POSTaggerConverter help|ad|conllx|parse|ontonotes|conllu [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>expandME</entry>
+  <entry>expandME</entry>
+  <entry>Yes</entry>
+  <entry>Expand multiword expressions.</entry>
+  </row>
+  <row>
+  <entry>includeFeatures</entry>
+  <entry>includeFeatures</entry>
+  <entry>Yes</entry>
+  <entry>Combine POS Tags with word features, like number and gender.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>conllx</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>parse</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>tagset</entry>
+  <entry>tagset</entry>
+  <entry>Yes</entry>
+  <entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.lemmatizer">
+
+  <title>Lemmatizer</title>
+
+  <section xml:id="tools.cli.lemmatizer.LemmatizerME">
+
+  <title>LemmatizerME</title>
+
+  <para>Learnable lemmatizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LemmatizerME model < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.lemmatizer.LemmatizerTrainerME">
+
+  <title>LemmatizerTrainerME</title>
+
+  <para>Trainer for the learnable lemmatizer</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LemmatizerTrainerME[.conllu] [-factory factoryName] [-params paramsFile] -lang language -model
+          modelFile -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of LemmatizerFactory where to get implementation and resources.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>tagset</entry>
+  <entry>tagset</entry>
+  <entry>Yes</entry>
+  <entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.lemmatizer.LemmatizerEvaluator">
+
+  <title>LemmatizerEvaluator</title>
+
+  <para>Measures the performance of the Lemmatizer model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp LemmatizerEvaluator[.conllu] -model model [-misclassified true|false] [-reportOutputFile
+          outputFile] -data sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -reportOutputFile outputFile
+      the path of the fine-grained report file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='2' valign='middle'>conllu</entry>
+  <entry>tagset</entry>
+  <entry>tagset</entry>
+  <entry>Yes</entry>
+  <entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.chunker">
+
+  <title>Chunker</title>
+
+  <section xml:id="tools.cli.chunker.ChunkerME">
+
+  <title>ChunkerME</title>
+
+  <para>Learnable chunker</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ChunkerME model < sentences]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.chunker.ChunkerTrainerME">
+
+  <title>ChunkerTrainerME</title>
+
+  <para>Trainer for the learnable chunker</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ChunkerTrainerME[.ad] [-factory factoryName] [-params paramsFile] -lang language -model
+          modelFile -data sampleData [-encoding charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of ChunkerFactory where to get implementation and resources.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>end</entry>
+  <entry>end</entry>
+  <entry>Yes</entry>
+  <entry>Index of last sentence</entry>
+  </row>
+  <row>
+  <entry>start</entry>
+  <entry>start</entry>
+  <entry>Yes</entry>
+  <entry>Index of first sentence</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.chunker.ChunkerEvaluator">
+
+  <title>ChunkerEvaluator</title>
+
+  <para>Measures the performance of the Chunker model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ChunkerEvaluator[.ad] -model model [-misclassified true|false] [-detailedF true|false] -data
+          sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -detailedF true|false
+      if true (default) will print detailed FMeasure results.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>end</entry>
+  <entry>end</entry>
+  <entry>Yes</entry>
+  <entry>Index of last sentence</entry>
+  </row>
+  <row>
+  <entry>start</entry>
+  <entry>start</entry>
+  <entry>Yes</entry>
+  <entry>Index of first sentence</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.chunker.ChunkerCrossValidator">
+
+  <title>ChunkerCrossValidator</title>
+
+  <para>K-fold cross validator for the chunker</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ChunkerCrossValidator[.ad] [-factory factoryName] [-params paramsFile] -lang language
+          [-misclassified true|false] [-folds num] [-detailedF true|false] -data sampleData [-encoding
+          charsetName]
+  Arguments description:
+    -factory factoryName
+      A sub-class of ChunkerFactory where to get implementation and resources.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -folds num
+      number of folds, default is 10.
+    -detailedF true|false
+      if true (default) will print detailed FMeasure results.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>end</entry>
+  <entry>end</entry>
+  <entry>Yes</entry>
+  <entry>Index of last sentence</entry>
+  </row>
+  <row>
+  <entry>start</entry>
+  <entry>start</entry>
+  <entry>Yes</entry>
+  <entry>Index of first sentence</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.chunker.ChunkerConverter">
+
+  <title>ChunkerConverter</title>
+
+  <para>Converts ad data format to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ChunkerConverter help|ad [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='4' valign='middle'>ad</entry>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>No</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  <row>
+  <entry>lang</entry>
+  <entry>language</entry>
+  <entry>No</entry>
+  <entry>Language which is being processed.</entry>
+  </row>
+  <row>
+  <entry>end</entry>
+  <entry>end</entry>
+  <entry>Yes</entry>
+  <entry>Index of last sentence</entry>
+  </row>
+  <row>
+  <entry>start</entry>
+  <entry>start</entry>
+  <entry>Yes</entry>
+  <entry>Index of first sentence</entry>
+  </row>
+  <row>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.parser">
+
+  <title>Parser</title>
+
+  <section xml:id="tools.cli.parser.Parser">
+
+  <title>Parser</title>
+
+  <para>Performs full syntactic parsing</para>
+
+  <screen>
+<![CDATA[Usage: opennlp Parser [-bs n -ap n -k n -tk tok_model] model < sentences
+  -bs n: Use a beam size of n.
+  -ap f: Advance outcomes in with at least f% of the probability mass.
+  -k n: Show the top n parses.  This will also display their log-probabilities.
+  -tk tok_model: Use the specified tokenizer model to tokenize the sentences. Defaults to a WhitespaceTokenizer.]]>
+  </screen>
+  </section>
+
+  <section xml:id="tools.cli.parser.ParserTrainer">
+
+  <title>ParserTrainer</title>
+
+  <para>Trains the learnable parser</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ParserTrainer[.ontonotes|.frenchtreebank] [-headRulesSerializerImpl className] -headRules
+          headRulesFile [-parserType CHUNKING|TREEINSERT] [-fun true|false] [-params paramsFile] -lang language
+          -model modelFile [-encoding charsetName] -data sampleData
+  Arguments description:
+    -headRulesSerializerImpl className
+      head rules artifact serializer class name
+    -headRules headRulesFile
+      head rules file.
+    -parserType CHUNKING|TREEINSERT
+      one of CHUNKING or TREEINSERT, default is CHUNKING.
+    -fun true|false
+      Learn to generate function tags.
+    -params paramsFile
+      training parameters file.
+    -lang language
+      language which is being processed.
+    -model modelFile
+      output model file.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.
+    -data sampleData
+      data to be used, usually a file name.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>frenchtreebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.parser.ParserEvaluator">
+
+  <title>ParserEvaluator</title>
+
+  <para>Measures the performance of the Parser model with the reference data</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ParserEvaluator[.ontonotes|.frenchtreebank] -model model [-misclassified true|false] -data
+          sampleData [-encoding charsetName]
+  Arguments description:
+    -model model
+      the model file to be evaluated.
+    -misclassified true|false
+      if true will print false negatives and false positives.
+    -data sampleData
+      data to be used, usually a file name.
+    -encoding charsetName
+      encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>frenchtreebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.parser.ParserConverter">
+
+  <title>ParserConverter</title>
+
+  <para>Converts foreign data formats (ontonotes,frenchtreebank) to native OpenNLP format</para>
+
+  <screen>
+<![CDATA[Usage: opennlp ParserConverter help|ontonotes|frenchtreebank [help|options...]]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>frenchtreebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.parser.BuildModelUpdater">
+
+  <title>BuildModelUpdater</title>
+
+  <para>Trains and updates the build model in a parser model</para>
+
+  <screen>
+<![CDATA[Usage: opennlp BuildModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang
+        language -data sampleData [-encoding charsetName]
 Arguments description:
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-factory factoryName
-		A sub-class of LanguageDetectorFactory where to get implementation and resources.
-	-params paramsFile
-		training parameters file.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>samplesPerLanguage</entry>
-<entry>samplesPerLanguage</entry>
-<entry>No</entry>
-<entry>Number of samples per language</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.langdetect.LanguageDetectorEvaluator'>
-
-<title>LanguageDetectorEvaluator</title>
-
-<para>Measures the performance of the Language Detector model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LanguageDetectorEvaluator[.leipzig] -model model [-misclassified true|false] 
-        [-reportOutputFile outputFile] -data sampleData [-encoding charsetName] 
+  -model modelFile
+    output model file.
+  -params paramsFile
+    training parameters file.
+  -lang language
+    language which is being processed.
+  -data sampleData
+    data to be used, usually a file name.
+  -encoding charsetName
+    encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead>
+    <row>
+      <entry>Format</entry>
+      <entry>Argument</entry>
+      <entry>Value</entry>
+      <entry>Optional</entry>
+      <entry>Description</entry>
+    </row>
+  </thead>
+  <tbody>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>frenchtreebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.parser.CheckModelUpdater">
+
+  <title>CheckModelUpdater</title>
+
+  <para>Trains and updates the check model in a parser model</para>
+
+  <screen>
+<![CDATA[Usage: opennlp CheckModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang
+        language -data sampleData [-encoding charsetName]
 Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>leipzig</entry>
-<entry>sentencesDir</entry>
-<entry>sentencesDir</entry>
-<entry>No</entry>
-<entry>Dir with Leipzig sentences to be used</entry>
-</row>
-<row>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>samplesPerLanguage</entry>
-<entry>samplesPerLanguage</entry>
-<entry>No</entry>
-<entry>Number of samples per language</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-</section>
-
-<section id='tools.cli.dictionary'>
-
-<title>Dictionary</title>
-
-<section id='tools.cli.dictionary.DictionaryBuilder'>
-
-<title>DictionaryBuilder</title>
-
-<para>Builds a new dictionary</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp DictionaryBuilder -outputFile out -inputFile in [-encoding charsetName]
-
-Arguments description:
-	-outputFile out
-		The dictionary file.
-	-inputFile in
-		Plain file with one entry per line
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-</section>
-
-</section>
-
-<section id='tools.cli.tokenizer'>
-
-<title>Tokenizer</title>
-
-<section id='tools.cli.tokenizer.SimpleTokenizer'>
-
-<title>SimpleTokenizer</title>
-
-<para>Character class tokenizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp SimpleTokenizer < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.tokenizer.TokenizerME'>
-
-<title>TokenizerME</title>
-
-<para>Learnable tokenizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenizerME model < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.tokenizer.TokenizerTrainer'>
-
-<title>TokenizerTrainer</title>
-
-<para>Trainer for the learnable tokenizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenizerTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] [-factory 
-        factoryName] [-abbDict path] [-alphaNumOpt isAlphaNumOpt] [-params paramsFile] -lang language -model 
-        modelFile -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of TokenizerFactory where to get implementation and resources.
-	-abbDict path
-		abbreviation dictionary in XML format.
-	-alphaNumOpt isAlphaNumOpt
-		Optimization flag to skip alpha numeric tokens for further tokenization
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllu</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.tokenizer.TokenizerMEEvaluator'>
-
-<title>TokenizerMEEvaluator</title>
-
-<para>Evaluator for the learnable tokenizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenizerMEEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] -model 
-        model [-misclassified true|false] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllu</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.tokenizer.TokenizerCrossValidator'>
-
-<title>TokenizerCrossValidator</title>
-
-<para>K-fold cross validator for the learnable tokenizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenizerCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] 
-        [-misclassified true|false] [-folds num] [-factory factoryName] [-abbDict path] [-alphaNumOpt 
-        isAlphaNumOpt] [-params paramsFile] -lang language -data sampleData [-encoding charsetName] 
-Arguments description:
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-factory factoryName
-		A sub-class of TokenizerFactory where to get implementation and resources.
-	-abbDict path
-		abbreviation dictionary in XML format.
-	-alphaNumOpt isAlphaNumOpt
-		Optimization flag to skip alpha numeric tokens for further tokenization
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllu</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.tokenizer.TokenizerConverter'>
-
-<title>TokenizerConverter</title>
-
-<para>Converts foreign data formats (irishsentencebank,ad,pos,conllx,namefinder,parse,conllu) to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenizerConverter help|irishsentencebank|ad|pos|conllx|namefinder|parse|conllu 
-        [help|options...] 
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllu</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.tokenizer.DictionaryDetokenizer'>
-
-<title>DictionaryDetokenizer</title>
-
-<para></para>
-
-<screen>
-<![CDATA[
-Usage: opennlp DictionaryDetokenizer detokenizerDictionary
-
-]]>
-</screen> 
-</section>
-
-</section>
-
-<section id='tools.cli.sentdetect'>
-
-<title>Sentdetect</title>
-
-<section id='tools.cli.sentdetect.SentenceDetector'>
-
-<title>SentenceDetector</title>
-
-<para>Learnable sentence detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp SentenceDetector model < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.sentdetect.SentenceDetectorTrainer'>
-
-<title>SentenceDetectorTrainer</title>
-
-<para>Trainer for the learnable sentence detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp 
-        SentenceDetectorTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt] 
-        [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language -model 
-        modelFile -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of SentenceDetectorFactory where to get implementation and resources.
-	-eosChars string
-		EOS characters.
-	-abbDict path
-		abbreviation dictionary in XML format.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>includeTitles</entry>
-<entry>includeTitles</entry>
-<entry>Yes</entry>
-<entry>If true will include sentences marked as headlines.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>moses</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>letsmt</entry>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>Yes</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.sentdetect.SentenceDetectorEvaluator'>
-
-<title>SentenceDetectorEvaluator</title>
-
-<para>Evaluator for the learnable sentence detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp 
-        SentenceDetectorEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt] 
-        -model model [-misclassified true|false] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>includeTitles</entry>
-<entry>includeTitles</entry>
-<entry>Yes</entry>
-<entry>If true will include sentences marked as headlines.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>moses</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>letsmt</entry>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>Yes</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.sentdetect.SentenceDetectorCrossValidator'>
-
-<title>SentenceDetectorCrossValidator</title>
-
-<para>K-fold cross validator for the learnable sentence detector</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp 
-        SentenceDetectorCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt] 
-        [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language 
-        [-misclassified true|false] [-folds num] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of SentenceDetectorFactory where to get implementation and resources.
-	-eosChars string
-		EOS characters.
-	-abbDict path
-		abbreviation dictionary in XML format.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>includeTitles</entry>
-<entry>includeTitles</entry>
-<entry>Yes</entry>
-<entry>If true will include sentences marked as headlines.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>moses</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>letsmt</entry>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>Yes</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.sentdetect.SentenceDetectorConverter'>
-
-<title>SentenceDetectorConverter</title>
-
-<para>Converts foreign data formats (irishsentencebank,ad,pos,conllx,namefinder,parse,moses,conllu,letsmt) to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp SentenceDetectorConverter 
-        help|irishsentencebank|ad|pos|conllx|namefinder|parse|moses|conllu|letsmt [help|options...] 
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='1' valign='middle'>irishsentencebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>includeTitles</entry>
-<entry>includeTitles</entry>
-<entry>Yes</entry>
-<entry>If true will include sentences marked as headlines.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>pos</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>namefinder</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>No</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>moses</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>sentencesPerSample</entry>
-<entry>sentencesPerSample</entry>
-<entry>No</entry>
-<entry>Number of sentences per sample</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>letsmt</entry>
-<entry>detokenizer</entry>
-<entry>dictionary</entry>
-<entry>Yes</entry>
-<entry>Specifies the file with detokenizer dictionary.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-</section>
-
-<section id='tools.cli.namefind'>
-
-<title>Namefind</title>
-
-<section id='tools.cli.namefind.TokenNameFinder'>
-
-<title>TokenNameFinder</title>
-
-<para>Learnable name finder</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenNameFinder model1 model2 ... modelN < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.namefind.TokenNameFinderTrainer'>
-
-<title>TokenNameFinderTrainer</title>
-
-<para>Trainer for the learnable name finder</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenNameFinderTrainer[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat] 
-        [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile] 
-        [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language -model modelFile -data 
-        sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of TokenNameFinderFactory
-	-resources resourcesDir
-		The resources directory
-	-type modelType
-		The type of the token name finder model
-	-featuregen featuregenFile
-		The feature generator descriptor file
-	-nameTypes types
-		name types to use for training
-	-sequenceCodec codec
-		sequence codec used to code name spans
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>evalita</entry>
-<entry>lang</entry>
-<entry>it</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,gpe</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll03</entry>
-<entry>lang</entry>
-<entry>eng|deu</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>bionlp2004</entry>
-<entry>types</entry>
-<entry>DNA,protein,cell_type,cell_line,RNA</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll02</entry>
-<entry>lang</entry>
-<entry>spa|nld</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>muc6</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='5' valign='middle'>brat</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>ruleBasedTokenizer</entry>
-<entry>name</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>annotationConfig</entry>
-<entry>annConfFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>bratDataDir</entry>
-<entry>bratDataDir</entry>
-<entry>No</entry>
-<entry>Location of brat data dir</entry>
-</row>
-<row>
-<entry>recursive</entry>
-<entry>value</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>sentenceDetectorModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.namefind.TokenNameFinderEvaluator'>
-
-<title>TokenNameFinderEvaluator</title>
-
-<para>Measures the performance of the NameFinder model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenNameFinderEvaluator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat] 
-        [-nameTypes types] -model model [-misclassified true|false] [-detailedF true|false] 
-        [-reportOutputFile outputFile] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-nameTypes types
-		name types to use for evaluation
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-detailedF true|false
-		if true (default) will print detailed FMeasure results.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>evalita</entry>
-<entry>lang</entry>
-<entry>it</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,gpe</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll03</entry>
-<entry>lang</entry>
-<entry>eng|deu</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>bionlp2004</entry>
-<entry>types</entry>
-<entry>DNA,protein,cell_type,cell_line,RNA</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll02</entry>
-<entry>lang</entry>
-<entry>spa|nld</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>muc6</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='5' valign='middle'>brat</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>ruleBasedTokenizer</entry>
-<entry>name</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>annotationConfig</entry>
-<entry>annConfFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>bratDataDir</entry>
-<entry>bratDataDir</entry>
-<entry>No</entry>
-<entry>Location of brat data dir</entry>
-</row>
-<row>
-<entry>recursive</entry>
-<entry>value</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>sentenceDetectorModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.namefind.TokenNameFinderCrossValidator'>
-
-<title>TokenNameFinderCrossValidator</title>
-
-<para>K-fold cross validator for the learnable Name Finder</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp 
-        TokenNameFinderCrossValidator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat] 
-        [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile] 
-        [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language [-misclassified 
-        true|false] [-folds num] [-detailedF true|false] [-reportOutputFile outputFile] -data sampleData 
-        [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of TokenNameFinderFactory
-	-resources resourcesDir
-		The resources directory
-	-type modelType
-		The type of the token name finder model
-	-featuregen featuregenFile
-		The feature generator descriptor file
-	-nameTypes types
-		name types to use for training
-	-sequenceCodec codec
-		sequence codec used to code name spans
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-detailedF true|false
-		if true (default) will print detailed FMeasure results.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>evalita</entry>
-<entry>lang</entry>
-<entry>it</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,gpe</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll03</entry>
-<entry>lang</entry>
-<entry>eng|deu</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>bionlp2004</entry>
-<entry>types</entry>
-<entry>DNA,protein,cell_type,cell_line,RNA</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll02</entry>
-<entry>lang</entry>
-<entry>spa|nld</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>muc6</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='5' valign='middle'>brat</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>ruleBasedTokenizer</entry>
-<entry>name</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>annotationConfig</entry>
-<entry>annConfFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>bratDataDir</entry>
-<entry>bratDataDir</entry>
-<entry>No</entry>
-<entry>Location of brat data dir</entry>
-</row>
-<row>
-<entry>recursive</entry>
-<entry>value</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>sentenceDetectorModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.namefind.TokenNameFinderConverter'>
-
-<title>TokenNameFinderConverter</title>
-
-<para>Converts foreign data formats (evalita,ad,conll03,bionlp2004,conll02,muc6,ontonotes,brat) to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TokenNameFinderConverter help|evalita|ad|conll03|bionlp2004|conll02|muc6|ontonotes|brat 
-        [help|options...] 
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='3' valign='middle'>evalita</entry>
-<entry>lang</entry>
-<entry>it</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,gpe</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>splitHyphenatedTokens</entry>
-<entry>split</entry>
-<entry>Yes</entry>
-<entry>If true all hyphenated tokens will be separated (default true)</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll03</entry>
-<entry>lang</entry>
-<entry>eng|deu</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>bionlp2004</entry>
-<entry>types</entry>
-<entry>DNA,protein,cell_type,cell_line,RNA</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='3' valign='middle'>conll02</entry>
-<entry>lang</entry>
-<entry>spa|nld</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>types</entry>
-<entry>per,loc,org,misc</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>muc6</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='5' valign='middle'>brat</entry>
-<entry>tokenizerModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>ruleBasedTokenizer</entry>
-<entry>name</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>annotationConfig</entry>
-<entry>annConfFile</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry>bratDataDir</entry>
-<entry>bratDataDir</entry>
-<entry>No</entry>
-<entry>Location of brat data dir</entry>
-</row>
-<row>
-<entry>recursive</entry>
-<entry>value</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-<row>
-<entry>sentenceDetectorModel</entry>
-<entry>modelFile</entry>
-<entry>Yes</entry>
-<entry></entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.namefind.CensusDictionaryCreator'>
-
-<title>CensusDictionaryCreator</title>
-
-<para>Converts 1990 US Census names into a dictionary</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp CensusDictionaryCreator [-encoding charsetName] [-lang code] -censusData censusDict -dict dict
-
-Arguments description:
-	-encoding charsetName
-	-lang code
-	-censusData censusDict
-	-dict dict
-
-]]>
-</screen> 
-</section>
-
-</section>
-
-<section id='tools.cli.postag'>
-
-<title>Postag</title>
-
-<section id='tools.cli.postag.POSTagger'>
-
-<title>POSTagger</title>
-
-<para>Learnable part of speech tagger</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp POSTagger model < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.postag.POSTaggerTrainer'>
-
-<title>POSTaggerTrainer</title>
-
-<para>Trains a model for the part-of-speech tagger</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp POSTaggerTrainer[.ad|.conllx|.parse|.ontonotes|.conllu] [-factory factoryName] [-resources 
-        resourcesDir] [-tagDictCutoff tagDictCutoff] [-featuregen featuregenFile] [-dict dictionaryPath] 
-        [-params paramsFile] -lang language -model modelFile -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of POSTaggerFactory where to get implementation and resources.
-	-resources resourcesDir
-		The resources directory
-	-tagDictCutoff tagDictCutoff
-		TagDictionary cutoff. If specified will create/expand a mutable TagDictionary
-	-featuregen featuregenFile
-		The feature generator descriptor file
-	-dict dictionaryPath
-		The XML tag dictionary file
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>expandME</entry>
-<entry>expandME</entry>
-<entry>Yes</entry>
-<entry>Expand multiword expressions.</entry>
-</row>
-<row>
-<entry>includeFeatures</entry>
-<entry>includeFeatures</entry>
-<entry>Yes</entry>
-<entry>Combine POS Tags with word features, like number and gender.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>tagset</entry>
-<entry>tagset</entry>
-<entry>Yes</entry>
-<entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.postag.POSTaggerEvaluator'>
-
-<title>POSTaggerEvaluator</title>
-
-<para>Measures the performance of the POS tagger model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp POSTaggerEvaluator[.ad|.conllx|.parse|.ontonotes|.conllu] -model model [-misclassified 
-        true|false] [-reportOutputFile outputFile] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>expandME</entry>
-<entry>expandME</entry>
-<entry>Yes</entry>
-<entry>Expand multiword expressions.</entry>
-</row>
-<row>
-<entry>includeFeatures</entry>
-<entry>includeFeatures</entry>
-<entry>Yes</entry>
-<entry>Combine POS Tags with word features, like number and gender.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>tagset</entry>
-<entry>tagset</entry>
-<entry>Yes</entry>
-<entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.postag.POSTaggerCrossValidator'>
-
-<title>POSTaggerCrossValidator</title>
-
-<para>K-fold cross validator for the learnable POS tagger</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp POSTaggerCrossValidator[.ad|.conllx|.parse|.ontonotes|.conllu] [-misclassified true|false] 
-        [-folds num] [-factory factoryName] [-resources resourcesDir] [-tagDictCutoff tagDictCutoff] 
-        [-featuregen featuregenFile] [-dict dictionaryPath] [-params paramsFile] -lang language 
-        [-reportOutputFile outputFile] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-factory factoryName
-		A sub-class of POSTaggerFactory where to get implementation and resources.
-	-resources resourcesDir
-		The resources directory
-	-tagDictCutoff tagDictCutoff
-		TagDictionary cutoff. If specified will create/expand a mutable TagDictionary
-	-featuregen featuregenFile
-		The feature generator descriptor file
-	-dict dictionaryPath
-		The XML tag dictionary file
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>expandME</entry>
-<entry>expandME</entry>
-<entry>Yes</entry>
-<entry>Expand multiword expressions.</entry>
-</row>
-<row>
-<entry>includeFeatures</entry>
-<entry>includeFeatures</entry>
-<entry>Yes</entry>
-<entry>Combine POS Tags with word features, like number and gender.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>tagset</entry>
-<entry>tagset</entry>
-<entry>Yes</entry>
-<entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.postag.POSTaggerConverter'>
-
-<title>POSTaggerConverter</title>
-
-<para>Converts foreign data formats (ad,conllx,parse,ontonotes,conllu) to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp POSTaggerConverter help|ad|conllx|parse|ontonotes|conllu [help|options...]
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>expandME</entry>
-<entry>expandME</entry>
-<entry>Yes</entry>
-<entry>Expand multiword expressions.</entry>
-</row>
-<row>
-<entry>includeFeatures</entry>
-<entry>includeFeatures</entry>
-<entry>Yes</entry>
-<entry>Combine POS Tags with word features, like number and gender.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>conllx</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>parse</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>tagset</entry>
-<entry>tagset</entry>
-<entry>Yes</entry>
-<entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-</section>
-
-<section id='tools.cli.lemmatizer'>
-
-<title>Lemmatizer</title>
-
-<section id='tools.cli.lemmatizer.LemmatizerME'>
-
-<title>LemmatizerME</title>
-
-<para>Learnable lemmatizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LemmatizerME model < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.lemmatizer.LemmatizerTrainerME'>
-
-<title>LemmatizerTrainerME</title>
-
-<para>Trainer for the learnable lemmatizer</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LemmatizerTrainerME[.conllu] [-factory factoryName] [-params paramsFile] -lang language -model 
-        modelFile -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of LemmatizerFactory where to get implementation and resources.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>tagset</entry>
-<entry>tagset</entry>
-<entry>Yes</entry>
-<entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.lemmatizer.LemmatizerEvaluator'>
-
-<title>LemmatizerEvaluator</title>
-
-<para>Measures the performance of the Lemmatizer model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp LemmatizerEvaluator[.conllu] -model model [-misclassified true|false] [-reportOutputFile 
-        outputFile] -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-reportOutputFile outputFile
-		the path of the fine-grained report file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='2' valign='middle'>conllu</entry>
-<entry>tagset</entry>
-<entry>tagset</entry>
-<entry>Yes</entry>
-<entry>U|x u for unified tags and x for language-specific part-of-speech tags</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-</section>
-
-<section id='tools.cli.chunker'>
-
-<title>Chunker</title>
-
-<section id='tools.cli.chunker.ChunkerME'>
-
-<title>ChunkerME</title>
-
-<para>Learnable chunker</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ChunkerME model < sentences
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.chunker.ChunkerTrainerME'>
-
-<title>ChunkerTrainerME</title>
-
-<para>Trainer for the learnable chunker</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ChunkerTrainerME[.ad] [-factory factoryName] [-params paramsFile] -lang language -model 
-        modelFile -data sampleData [-encoding charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of ChunkerFactory where to get implementation and resources.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>end</entry>
-<entry>end</entry>
-<entry>Yes</entry>
-<entry>Index of last sentence</entry>
-</row>
-<row>
-<entry>start</entry>
-<entry>start</entry>
-<entry>Yes</entry>
-<entry>Index of first sentence</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.chunker.ChunkerEvaluator'>
-
-<title>ChunkerEvaluator</title>
-
-<para>Measures the performance of the Chunker model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ChunkerEvaluator[.ad] -model model [-misclassified true|false] [-detailedF true|false] -data 
-        sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-detailedF true|false
-		if true (default) will print detailed FMeasure results.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>end</entry>
-<entry>end</entry>
-<entry>Yes</entry>
-<entry>Index of last sentence</entry>
-</row>
-<row>
-<entry>start</entry>
-<entry>start</entry>
-<entry>Yes</entry>
-<entry>Index of first sentence</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.chunker.ChunkerCrossValidator'>
-
-<title>ChunkerCrossValidator</title>
-
-<para>K-fold cross validator for the chunker</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ChunkerCrossValidator[.ad] [-factory factoryName] [-params paramsFile] -lang language 
-        [-misclassified true|false] [-folds num] [-detailedF true|false] -data sampleData [-encoding 
-        charsetName] 
-Arguments description:
-	-factory factoryName
-		A sub-class of ChunkerFactory where to get implementation and resources.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-folds num
-		number of folds, default is 10.
-	-detailedF true|false
-		if true (default) will print detailed FMeasure results.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>end</entry>
-<entry>end</entry>
-<entry>Yes</entry>
-<entry>Index of last sentence</entry>
-</row>
-<row>
-<entry>start</entry>
-<entry>start</entry>
-<entry>Yes</entry>
-<entry>Index of first sentence</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.chunker.ChunkerConverter'>
-
-<title>ChunkerConverter</title>
-
-<para>Converts ad data format to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ChunkerConverter help|ad [help|options...]
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='4' valign='middle'>ad</entry>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>No</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-<row>
-<entry>lang</entry>
-<entry>language</entry>
-<entry>No</entry>
-<entry>Language which is being processed.</entry>
-</row>
-<row>
-<entry>end</entry>
-<entry>end</entry>
-<entry>Yes</entry>
-<entry>Index of last sentence</entry>
-</row>
-<row>
-<entry>start</entry>
-<entry>start</entry>
-<entry>Yes</entry>
-<entry>Index of first sentence</entry>
-</row>
-<row>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-</section>
-
-<section id='tools.cli.parser'>
-
-<title>Parser</title>
-
-<section id='tools.cli.parser.Parser'>
-
-<title>Parser</title>
-
-<para>Performs full syntactic parsing</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp Parser [-bs n -ap n -k n -tk tok_model] model < sentences 
--bs n: Use a beam size of n.
--ap f: Advance outcomes in with at least f% of the probability mass.
--k n: Show the top n parses.  This will also display their log-probabilities.
--tk tok_model: Use the specified tokenizer model to tokenize the sentences. Defaults to a WhitespaceTokenizer.
-
-]]>
-</screen> 
-</section>
-
-<section id='tools.cli.parser.ParserTrainer'>
-
-<title>ParserTrainer</title>
-
-<para>Trains the learnable parser</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ParserTrainer[.ontonotes|.frenchtreebank] [-headRulesSerializerImpl className] -headRules 
-        headRulesFile [-parserType CHUNKING|TREEINSERT] [-fun true|false] [-params paramsFile] -lang language 
-        -model modelFile [-encoding charsetName] -data sampleData 
-Arguments description:
-	-headRulesSerializerImpl className
-		head rules artifact serializer class name
-	-headRules headRulesFile
-		head rules file.
-	-parserType CHUNKING|TREEINSERT
-		one of CHUNKING or TREEINSERT, default is CHUNKING.
-	-fun true|false
-		Learn to generate function tags.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-	-data sampleData
-		data to be used, usually a file name.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>frenchtreebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.parser.ParserEvaluator'>
-
-<title>ParserEvaluator</title>
-
-<para>Measures the performance of the Parser model with the reference data</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ParserEvaluator[.ontonotes|.frenchtreebank] -model model [-misclassified true|false] -data 
-        sampleData [-encoding charsetName] 
-Arguments description:
-	-model model
-		the model file to be evaluated.
-	-misclassified true|false
-		if true will print false negatives and false positives.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>frenchtreebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.parser.ParserConverter'>
-
-<title>ParserConverter</title>
-
-<para>Converts foreign data formats (ontonotes,frenchtreebank) to native OpenNLP format</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp ParserConverter help|ontonotes|frenchtreebank [help|options...]
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>frenchtreebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.parser.BuildModelUpdater'>
-
-<title>BuildModelUpdater</title>
-
-<para>Trains and updates the build model in a parser model</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp BuildModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang 
-        language -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model modelFile
-		output model file.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>frenchtreebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.parser.CheckModelUpdater'>
-
-<title>CheckModelUpdater</title>
-
-<para>Trains and updates the check model in a parser model</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp CheckModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang 
-        language -data sampleData [-encoding charsetName] 
-Arguments description:
-	-model modelFile
-		output model file.
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-data sampleData
-		data to be used, usually a file name.
-	-encoding charsetName
-		encoding for reading and writing text, if absent the system default is used.
-
-]]>
-</screen> 
-<para>The supported formats and arguments are:</para>
-
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
-<tbody>
-<row>
-<entry morerows='0' valign='middle'>ontonotes</entry>
-<entry>ontoNotesDir</entry>
-<entry>OntoNotes 4.0 corpus directory</entry>
-<entry>No</entry>
-<entry></entry>
-</row>
-<row>
-<entry morerows='1' valign='middle'>frenchtreebank</entry>
-<entry>data</entry>
-<entry>sampleData</entry>
-<entry>No</entry>
-<entry>Data to be used, usually a file name.</entry>
-</row>
-<row>
-<entry>encoding</entry>
-<entry>charsetName</entry>
-<entry>Yes</entry>
-<entry>Encoding for reading and writing text, if absent the system default is used.</entry>
-</row>
-</tbody>
-</tgroup></informaltable>
-
-</section>
-
-<section id='tools.cli.parser.TaggerModelReplacer'>
-
-<title>TaggerModelReplacer</title>
-
-<para>Replaces the tagger model in a parser model</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp TaggerModelReplacer parser.model tagger.model
-
-]]>
-</screen> 
-</section>
-
-</section>
-
-<section id='tools.cli.entitylinker'>
-
-<title>Entitylinker</title>
-
-<section id='tools.cli.entitylinker.EntityLinker'>
-
-<title>EntityLinker</title>
-
-<para>Links an entity to an external data set</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp EntityLinker model < sentences
-
-]]>
-</screen> 
-</section>
-
-</section>
-
-<section id='tools.cli.languagemodel'>
-
-<title>Languagemodel</title>
-
-<section id='tools.cli.languagemodel.NGramLanguageModel'>
-
-<title>NGramLanguageModel</title>
-
-<para>Gives the probability and most probable next token(s) of a sequence of tokens in a language model</para>
-
-<screen>
-<![CDATA[
-Usage: opennlp NGramLanguageModel model
-
-]]>
-</screen> 
-</section>
-
-</section>
-
-
-
+  -model modelFile
+    output model file.
+  -params paramsFile
+    training parameters file.
+  -lang language
+    language which is being processed.
+  -data sampleData
+    data to be used, usually a file name.
+  -encoding charsetName
+    encoding for reading and writing text, if absent the system default is used.]]>
+  </screen>
+  <para>The supported formats and arguments are:</para>
+
+  <informaltable frame='all'>
+  <tgroup cols='5' align='left' colsep='1' rowsep='1'>
+  <thead><row>
+    <entry>Format</entry>
+    <entry>Argument</entry>
+    <entry>Value</entry>
+    <entry>Optional</entry>
+    <entry>Description</entry></row></thead>
+  <tbody>
+  <row>
+  <entry morerows='0' valign='middle'>ontonotes</entry>
+  <entry>ontoNotesDir</entry>
+  <entry>OntoNotes 4.0 corpus directory</entry>
+  <entry>No</entry>
+  <entry></entry>
+  </row>
+  <row>
+  <entry morerows='1' valign='middle'>frenchtreebank</entry>
+  <entry>data</entry>
+  <entry>sampleData</entry>
+  <entry>No</entry>
+  <entry>Data to be used, usually a file name.</entry>
+  </row>
+  <row>
+  <entry>encoding</entry>
+  <entry>charsetName</entry>
+  <entry>Yes</entry>
+  <entry>Encoding for reading and writing text, if absent the system default is used.</entry>
+  </row>
+  </tbody>
+  </tgroup></informaltable>
+
+  </section>
+
+  <section xml:id="tools.cli.parser.TaggerModelReplacer">
+
+  <title>TaggerModelReplacer</title>
+
+  <para>Replaces the tagger model in a parser model</para>
+
+  <screen>
+<![CDATA[Usage: opennlp TaggerModelReplacer parser.model tagger.model]]>
+  </screen>
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.entitylinker">
+
+  <title>Entitylinker</title>
+
+  <section xml:id="tools.cli.entitylinker.EntityLinker">
+
+  <title>EntityLinker</title>
+
+  <para>Links an entity to an external data set</para>
+
+  <screen>
+<![CDATA[Usage: opennlp EntityLinker model < sentences]]>
+  </screen>
+  </section>
+
+  </section>
+
+  <section xml:id="tools.cli.languagemodel">
+
+  <title>Languagemodel</title>
+
+  <section xml:id="tools.cli.languagemodel.NGramLanguageModel">
+
+  <title>NGramLanguageModel</title>
+
+  <para>Gives the probability and most probable next token(s) of a sequence of tokens in a language model</para>
+
+  <screen>
+<![CDATA[Usage: opennlp NGramLanguageModel model]]>
+  </screen>
+  </section>
+
+  </section>
 </chapter>
diff --git a/opennlp-docs/src/docbkx/coref.xml b/opennlp-docs/src/docbkx/coref.xml
index d28ce9c9..08ffb1e7 100644
--- a/opennlp-docs/src/docbkx/coref.xml
+++ b/opennlp-docs/src/docbkx/coref.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://cdn.docbook.org/schema/5.0/dtd/docbook.dtd"[
 ]>
 <!--
 Licensed to the Apache Software Foundation (ASF) under one
@@ -21,55 +21,55 @@ specific language governing permissions and limitations
 under the License.
 -->
 
-<chapter id="tools.coref">
-<title>Coreference Resolution</title>
-<para>
-The OpenNLP Coreference Resolution system links multiple mentions of an
-entity in a document together.
-The OpenNLP implementation is currently limited to noun phrase mentions,
-other mention types cannot be resolved.
-</para>
+<chapter xml:id="tools.coref" xmlns:xlink="http://www.w3.org/1999/xlink">
+  <title>Coreference Resolution</title>
+  <para>
+  The OpenNLP Coreference Resolution system links multiple mentions of an
+  entity in a document together.
+  The OpenNLP implementation is currently limited to noun phrase mentions,
+  other mention types cannot be resolved.
+  </para>
 
-<para>
-TODO: Write more documentation about the coref component. Any contributions
-are very welcome. If you want to contribute please contact us on the mailing list
-or comment on the jira issue <ulink url="https://issues.apache.org/jira/browse/OPENNLP-48">OPENNLP-48</ulink>.
-</para>
-<!--
-<section id="tools.coref.implementation">
-	<title>Implementation</title>
-	<para>The following section gives an overview of the implementation.
-	The process is divided in two steps. First mention which can be linked
-	are identified and in a second step a set of specialized resolvers links them together.
-	</para>
+  <para>
+  TODO: Write more documentation about the coref component. Any contributions
+  are very welcome. If you want to contribute please contact us on the mailing list
+  or comment on the jira issue <link xlink:href="https://issues.apache.org/jira/browse/OPENNLP-48">OPENNLP-48</link>.
+  </para>
+  <!--
+  <section xml:id="tools.coref.implementation">
+    <title>Implementation</title>
+    <para>The following section gives an overview of the implementation.
+    The process is divided in two steps. First mention which can be linked
+    are identified and in a second step a set of specialized resolvers links them together.
+    </para>
+
+    <section xml:id="tools.coref.implementation.mention_finding">
+    <title>Mention Finding</title>
+    <para>
+    </para>
+    </section>
 
-	<section id="tools.coref.implementation.mention_finding">
-	<title>Mention Finding</title>
-	<para>
-	</para>
-	</section>
+    <section xml:id="tools.coref.implementation.linking">
+    <title>Linking</title>
+    <para>
+    Resolvers and linking:
+    The implementation has a dedicated model for different mention
+    categories.
+    These are:
+    Common Nouns
+    Definite Nouns
+    Plural Nouns
+    Plural Pronouns
+    Proper Nouns
+    Singular Pronouns
+    Speech Pronouns
 
-	<section id="tools.coref.implementation.linking">
-	<title>Linking</title>
-	<para>
-Resolvers and linking:
-The implementation has a dedicated model for different mention
-categories.
-These are:
-Common Nouns
-Definite Nouns
-Plural Nouns
-Plural Pronouns
-Proper Nouns
-Singular Pronouns
-Speech Pronouns
+  - speak about 7 seven different models ...
+  - explain non referential thing
+  - speak about number, gender and similarity
+  - Speak about mention finding
 
-- speak about 7 seven different models ...
-- explain non referential thing
-- speak about number, gender and similarity
-- Speak about mention finding
-	
-	</para>
-	</section>  
-</section> --> 
+    </para>
+    </section>
+  </section> -->
 </chapter>
\ No newline at end of file
diff --git a/opennlp-docs/src/docbkx/corpora.xml b/opennlp-docs/src/docbkx/corpora.xml
index d420ca74..ae15073c 100644
--- a/opennlp-docs/src/docbkx/corpora.xml
+++ b/opennlp-docs/src/docbkx/corpora.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://cdn.docbook.org/schema/5.0/dtd/docbook.dtd"[
 ]>
 <!--
 Licensed to the Apache Software Foundation (ASF) under one
@@ -21,14 +21,14 @@ specific language governing permissions and limitations
 under the License.
 -->
 
-<chapter id="tools.corpora">
+<chapter xml:id="tools.corpora" xmlns:xlink="http://www.w3.org/1999/xlink">
 
 	<title>Corpora</title>
 	<para>
-	    OpenNLP has built-in support to convert into the native training format or directly use
-        various corpora	needed by the different	trainable components.
+	OpenNLP has built-in support to convert into the native training format or directly use
+	various corpora	needed by the different	trainable components.
 	</para>
-	<section id="tools.corpora.conll">
+	<section xml:id="tools.corpora.conll">
 		<title>CONLL</title>
 		<para>
 		CoNLL stands for the Conference on Computational Natural Language Learning and is not
@@ -36,12 +36,13 @@ under the License.
 		environment. More information about the entire conference series can be obtained here
 		for CoNLL.
 		</para>
-		<section id="tools.corpora.conll.2000">
+		<section xml:id="tools.corpora.conll.2000">
 		<title>CONLL 2000</title>
 		<para>
 		The shared task of CoNLL-2000 is Chunking.
 		</para>
-		<section id="tools.corpora.conll.2000.getting">
+			
+		<section xml:id="tools.corpora.conll.2000.getting">
 		<title>Getting the data</title>
 		<para>
 		CoNLL-2000 made available training and test data for the Chunk task in English. 
@@ -50,28 +51,32 @@ under the License.
 		(211727 tokens) and section 20 as test data (47377 tokens). The annotation of the 
 		data has been derived from the WSJ corpus by a program written by Sabine Buchholz 
 		from Tilburg University, The Netherlands. Both training and test data can be
-		obtained from <ulink url="https://www.clips.uantwerpen.be/conll2000/chunking/">https://www.clips.uantwerpen.be/conll2000/chunking/</ulink>.
+		obtained from 
+			<link xlink:href="https://www.clips.uantwerpen.be/conll2000/chunking/">
+				https://www.clips.uantwerpen.be/conll2000/chunking/
+			</link>.
 		</para>
 		</section>
-		<section id="tools.corpora.conll.2000.converting">
+
+		<section xml:id="tools.corpora.conll.2000.converting">
 		<title>Converting the data</title>
 		<para>
-		The data don't need to be transformed because Apache OpenNLP Chunker follows
-		the CONLL 2000 format for training. Check <link linkend="tools.chunker.training">Chunker Training</link> section to learn more.
+			The data don't need to be transformed because Apache OpenNLP Chunker follows
+			the CONLL 2000 format for training. Check <xref linkend="tools.chunker.training">Chunker Training</xref>
+			section to learn more.
 		</para>
 		</section>
-		<section id="tools.corpora.conll.2000.training">
+
+		<section xml:id="tools.corpora.conll.2000.training">
 		<title>Training</title>
 		<para>
-		 We can train the model for the Chunker using the train.txt available at CONLL 2000:
-		 <screen>
-			<![CDATA[
-$ opennlp ChunkerTrainerME -model en-chunker.bin -iterations 500 \
+			We can train the model for the Chunker using the train.txt available at CONLL 2000:
+		 	<screen>
+<![CDATA[$ opennlp ChunkerTrainerME -model en-chunker.bin -iterations 500 \
                            -lang en -data train.txt -encoding UTF-8]]>
-		</screen>
-		<screen>
-			<![CDATA[
-Indexing events using cutoff of 5
+			</screen>
+			<screen>
+<![CDATA[Indexing events using cutoff of 5
 
 	Computing event counts...  done. 211727 events
 	Indexing...  done.
@@ -96,20 +101,19 @@ Performing 500 iterations.
 Writing chunker model ... done (4.019s)
 
 Wrote chunker model to path: .\en-chunker.bin]]>
-		</screen>
-		</para>
+			</screen>
+			</para>
 		</section>
-		<section id="tools.corpora.conll.2000.evaluation">
+
+		<section xml:id="tools.corpora.conll.2000.evaluation">
 		<title>Evaluating</title>
 		<para>
 		We evaluate the model using the file test.txt  available at CONLL 2000:
 		<screen>
-			<![CDATA[
-$ opennlp ChunkerEvaluator -model en-chunker.bin -lang en -encoding utf8 -data test.txt]]>
+<![CDATA[$ opennlp ChunkerEvaluator -model en-chunker.bin -lang en -encoding utf8 -data test.txt]]>
 		</screen>
 		<screen>
-			<![CDATA[
-Loading Chunker model ... done (0,665s)
+<![CDATA[Loading Chunker model ... done (0,665s)
 current: 85,8 sent/s avg: 85,8 sent/s total: 86 sent
 current: 88,1 sent/s avg: 87,0 sent/s total: 174 sent
 current: 156,2 sent/s avg: 110,0 sent/s total: 330 sent
@@ -135,12 +139,12 @@ F-Measure: 0.9230575441395671]]>
 		</para>
 		</section>
 	</section>
-		<section id="tools.corpora.conll.2002">
+		<section xml:id="tools.corpora.conll.2002">
 		<title>CONLL 2002</title>
 		<para>
 		The shared task of CoNLL-2002 is language independent named entity recognition for Spanish and Dutch.
 		</para>
-		<section id="tools.corpora.conll.2002.getting">
+		<section xml:id="tools.corpora.conll.2002.getting">
 		<title>Getting the data</title>
 		<para>The data consists of three files per language: one training file and two test files testa and testb.
 		The first test file will be used in the development phase for finding good parameters for the learning system.
@@ -149,52 +153,48 @@ F-Measure: 0.9230575441395671]]>
 		</para>
 		<para>
 		The Spanish data is a collection of newswire articles made available by the Spanish EFE News Agency. The articles are
-		from May 2000. The annotation was carried out by the <ulink url="https://www.talp.cat/">TALP Research Center</ulink> of the Technical University of Catalonia (UPC)
-		and the <ulink url="https://web.archive.org/web/20220516042208/http://clic.ub.edu/">Center of Language and Computation (CLiC)</ulink>of the University of Barcelona (UB), and funded by the European Commission
+		from May 2000. The annotation was carried out by the <link xlink:href="https://www.talp.cat/">TALP Research Center</link> of the Technical University of Catalonia (UPC)
+		and the <link xlink:href="https://web.archive.org/web/20220516042208/http://clic.ub.edu/">Center of Language and Computation (CLiC)</link>of the University of Barcelona (UB), and funded by the European Commission
 		through the NAMIC project (IST-1999-12392). 
 		</para>
 		<para>
 		The Dutch data consist of four editions of the Belgian newspaper "De Morgen" of 2000 (June 2, July 1, August 1 and September 1).
-		The data was annotated as a part of the <ulink url="http://atranos.esat.kuleuven.ac.be/">Atranos</ulink> project at the University of Antwerp. 
+		The data was annotated as a part of the <link xlink:href="https://atranos.esat.kuleuven.ac.be/">Atranos</link> project at the University of Antwerp.
 		</para>
 		<para>
 		You can find the Spanish files here: 
-		<ulink url="https://www.lsi.upc.edu/~nlp/tools/nerc/nerc.html">https://www.lsi.upc.edu/~nlp/tools/nerc/nerc.html</ulink>
+		<link xlink:href="https://www.lsi.upc.edu/~nlp/tools/nerc/nerc.html">https://www.lsi.upc.edu/~nlp/tools/nerc/nerc.html</link>
 		You must download esp.train.gz, unzip it and you will see the file esp.train.
 		</para>
 		<para>
 		You can find the Dutch files here: 
-		<ulink url="https://www.cnts.ua.ac.be/conll2002/ner.tgz">https://www.cnts.ua.ac.be/conll2002/ner.tgz</ulink>
+		<link xlink:href="https://www.cnts.ua.ac.be/conll2002/ner.tgz">https://www.cnts.ua.ac.be/conll2002/ner.tgz</link>
 		You must unzip it and go to /ner/data/ned.train.gz, so you unzip it too, and you will see the file ned.train.
 		</para>
 		</section>
-		<section id="tools.corpora.conll.2002.converting">
+		<section xml:id="tools.corpora.conll.2002.converting">
 		<title>Converting the data</title>
 		<para>
 		I will use Spanish data as reference, but it would be the same operations to Dutch. You just must remember change “-lang es” to “-lang nl” and use
 		the correct training files. So to convert the information to the OpenNLP format: 
 		<screen>
-			<![CDATA[
-$ opennlp TokenNameFinderConverter conll02 -data esp.train -lang es -types per > es_corpus_train_persons.txt]]>
+<![CDATA[$ opennlp TokenNameFinderConverter conll02 -data esp.train -lang es -types per > es_corpus_train_persons.txt]]>
 		</screen>
 		Optionally, you can convert the training test samples as well.
 		<screen>
-			<![CDATA[
-$ opennlp TokenNameFinderConverter conll02 -data esp.testa -lang es -types per > corpus_testa.txt
+<![CDATA[$ opennlp TokenNameFinderConverter conll02 -data esp.testa -lang es -types per > corpus_testa.txt
 $ opennlp TokenNameFinderConverter conll02 -data esp.testb -lang es -types per > corpus_testb.txt]]>
 		</screen>
 		</para>
 		</section>
-		<section id="tools.corpora.conll.2002.training.spanish">
+		<section xml:id="tools.corpora.conll.2002.training.spanish">
 		<title>Training with Spanish data</title>
 		<para>
 		To train the model for the name finder: 
 		<screen>
-			<![CDATA[
-\bin\opennlp TokenNameFinderTrainer -lang es -encoding u
+<![CDATA[\bin\opennlp TokenNameFinderTrainer -lang es -encoding u
 tf8 -iterations 500 -data es_corpus_train_persons.txt -model es_ner_person.bin
 
-
 Indexing events using cutoff of 5
 
         Computing event counts...  done. 264715 events
@@ -249,70 +249,68 @@ path: .\es_ner_person.bin]]>
 		</section>
 		</section>
 		
-		<section id="tools.corpora.conll.2003">
+		<section xml:id="tools.corpora.conll.2003">
 		<title>CONLL 2003</title>
 		<para>
 		The shared task of CoNLL-2003 is language independent named entity recognition
 		for English and German.
 		</para>
-		<section id="tools.corpora.conll.2003.getting">
+		<section xml:id="tools.corpora.conll.2003.getting">
 		<title>Getting the data</title>
 		<para>
 		The English data is the Reuters Corpus, which is a collection of newswire articles.
 		The Reuters Corpus can be obtained free of charges from the NIST for research
-		purposes: <ulink url="https://trec.nist.gov/data/reuters/reuters.html">https://trec.nist.gov/data/reuters/reuters.html</ulink>
+		purposes: <link xlink:href="https://trec.nist.gov/data/reuters/reuters.html">https://trec.nist.gov/data/reuters/reuters.html</link>
 		</para>
 		<para>
 		The German data is a collection of articles from the German newspaper Frankfurter
 		Rundschau. The articles are part of the ECI Multilingual Text Corpus which
 		can be obtained for 75$ (2010) from the Linguistic Data Consortium:
-<ulink url="http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC94T5">http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC94T5</ulink>		</para>
+			<link xlink:href="https://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC94T5">
+				https://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC94T5
+			</link>
+		</para>
 		<para>After one of the corpora is available the data must be
 		transformed as explained in the README file to the CONLL format.
 		The transformed data can be read by the OpenNLP CONLL03 converter.
-
-      Note that for CoNLL-2003 corpora, the -lang argument should either be "eng" or "deu", instead of "en" or "de".
+		Note that for CoNLL-2003 corpora, the -lang argument should either be "eng" or "deu", instead of "en" or "de".
 		</para>
 		</section>
-		<section id="tools.corpora.conll.2003.converting">
+			
+		<section xml:id="tools.corpora.conll.2003.converting">
 		<title>Converting the data (optional)</title>
 		<para>
 		To convert the information to the OpenNLP format:
 		<screen>
-			<![CDATA[
-$ opennlp TokenNameFinderConverter conll03 -lang eng -types per -data corpus_train.txt > eng.train]]>
+<![CDATA[$ opennlp TokenNameFinderConverter conll03 -lang eng -types per -data corpus_train.txt > eng.train]]>
 		</screen>
 		Optionally, you can convert the training test samples as well.
 		<screen>
-			<![CDATA[
-$ opennlp TokenNameFinderConverter conll03 -lang eng -types per -data corpus_testa.txt > eng.testa
+<![CDATA[$ opennlp TokenNameFinderConverter conll03 -lang eng -types per -data corpus_testa.txt > eng.testa
 $ opennlp TokenNameFinderConverter conll03 -lang eng -types per -data corpus_testb.txt > eng.testb]]>
 		</screen>
 		</para>
 		</section>
-		<section id="tools.corpora.conll.2003.training.english">
+		<section xml:id="tools.corpora.conll.2003.training.english">
 		<title>Training with English data</title>
             <para>
                 You can train the model for the name finder this way:
                 <screen>
-                <![CDATA[
-$ opennlp TokenNameFinderTrainer.conll03 -model en_ner_person.bin \
+<![CDATA[$ opennlp TokenNameFinderTrainer.conll03 -model en_ner_person.bin \
                                  -lang eng -types per -data eng.train -encoding utf8]]>
                 </screen>
             </para>
 		    <para>
                 If you have converted the data, then you can train the model for the name finder this way:
                 <screen>
-                <![CDATA[
-$ opennlp TokenNameFinderTrainer.conll03 -model en_ner_person.bin \
+<![CDATA[$ opennlp TokenNameFinderTrainer.conll03 -model en_ner_person.bin \
                                  -lang eng -types per -data corpus_train.txt -encoding utf8]]>
 		        </screen>
             </para>
             <para>
                 Either way you should see the following output during the training process:
 		        <screen>
-			    <![CDATA[
-Indexing events with TwoPass using cutoff of 0
+<![CDATA[Indexing events with TwoPass using cutoff of 0
 
 	Computing event counts...  done. 203621 events
 	Indexing...  done.
@@ -356,33 +354,28 @@ Execution time: 11,498 seconds]]>
 		        </screen>
 		    </para>
 		</section>
-		<section id="tools.corpora.conll.2003.evaluation.english">
+		<section xml:id="tools.corpora.conll.2003.evaluation.english">
 		<title>Evaluating with English data</title>
             <para>
                 You can evaluate the model for the name finder this way:
                 <screen>
-                <![CDATA[
-$ opennlp TokenNameFinderEvaluator.conll03 -model en_ner_person.bin \
+<![CDATA[$ opennlp TokenNameFinderEvaluator.conll03 -model en_ner_person.bin \
                                    -lang eng -types per -data eng.testa -encoding utf8]]>
                 </screen>
             </para>
 		    <para>
-		        If you converted the test A and B files above, you can use them to evaluate the
-                model.
+		        If you converted the test A and B files above, you can use them to evaluate the model.
 		        <screen>
-			<![CDATA[
-$ opennlp TokenNameFinderEvaluator.conll03 -model en_ner_person.bin \
+<![CDATA[$ opennlp TokenNameFinderEvaluator.conll03 -model en_ner_person.bin \
                                    -lang eng -types per -data corpus_testa.txt -encoding utf8]]>
 		        </screen>
             </para>
             <para>
                 Either way you should see the following output:
 		        <screen>
-			<![CDATA[
-Loading Token Name Finder model ... done (0,176s)
+<![CDATA[Loading Token Name Finder model ... done (0,176s)
 current: 1805,4 sent/s avg: 1805,4 sent/s total: 1961 sent
 
-
 Average: 2298,1 sent/s
 Total: 3454 sent
 Runtime: 1.503s
@@ -397,51 +390,47 @@ Execution time: 1,955 seconds]]>
 		</section>
 	</section>
 	</section>
-	<section id="tools.corpora.arvores-deitadas">
+	<section xml:id="tools.corpora.arvores-deitadas">
 		<title>Arvores Deitadas</title>
 		<para>
-		The Portuguese corpora available at <ulink url="https://www.linguateca.pt">Floresta Sintá(c)tica</ulink> project follow the Arvores Deitadas (AD) format. Apache OpenNLP includes tools to convert from AD format to native format.
+		The Portuguese corpora available at <link xlink:href="https://www.linguateca.pt">Floresta Sintá(c)tica</link> project follow the Arvores Deitadas (AD) format. Apache OpenNLP includes tools to convert from AD format to native format.
 		</para>		
-		<section id="tools.corpora.arvores-deitadas.getting">
+		<section xml:id="tools.corpora.arvores-deitadas.getting">
 			<title>Getting the data</title>
 			<para>
-			The Corpus can be downloaded from here: <ulink url="https://www.linguateca.pt/floresta/corpus.html">https://www.linguateca.pt/floresta/corpus.html</ulink>
+			The Corpus can be downloaded from here: <link xlink:href="https://www.linguateca.pt/floresta/corpus.html">https://www.linguateca.pt/floresta/corpus.html</link>
 			</para>
 			<para>
-			The Name Finder models were trained using the Amazonia corpus: <ulink url="https://www.linguateca.pt/floresta/ficheiros/gz/amazonia.ad.gz">amazonia.ad</ulink>.
-			The Chunker models were trained using the <ulink url="https://www.linguateca.pt/floresta/ficheiros/gz/Bosque_CF_8.0.ad.txt.gz">Bosque_CF_8.0.ad</ulink>.
+			The Name Finder models were trained using the Amazonia corpus: <link xlink:href="https://www.linguateca.pt/floresta/ficheiros/gz/amazonia.ad.gz">amazonia.ad</link>.
+			The Chunker models were trained using the <link xlink:href="https://www.linguateca.pt/floresta/ficheiros/gz/Bosque_CF_8.0.ad.txt.gz">Bosque_CF_8.0.ad</link>.
 			</para>
 		</section>
 		
-		<section id="tools.corpora.arvores-deitadas.converting">
+		<section xml:id="tools.corpora.arvores-deitadas.converting">
 			<title>Converting the data (optional)</title>
 			    <para>
 				    To extract NameFinder training data from Amazonia corpus:
 			        <screen>
-			        <![CDATA[
-$ opennlp TokenNameFinderConverter ad -lang pt -encoding ISO-8859-1 -data amazonia.ad > corpus.txt]]>
+<![CDATA[$ opennlp TokenNameFinderConverter ad -lang pt -encoding ISO-8859-1 -data amazonia.ad > corpus.txt]]>
 			        </screen>
 			</para>
 			<para>
 				To extract Chunker training data from Bosque_CF_8.0.ad corpus:
 			    <screen>
-			    <![CDATA[
-$ opennlp ChunkerConverter ad -lang pt -data Bosque_CF_8.0.ad.txt -encoding ISO-8859-1 > bosque-chunk]]>
+<![CDATA[$ opennlp ChunkerConverter ad -lang pt -data Bosque_CF_8.0.ad.txt -encoding ISO-8859-1 > bosque-chunk]]>
     			</screen>
 			</para>
 		</section>
-		<section id="tools.corpora.arvores-deitadas.evaluation">
+		<section xml:id="tools.corpora.arvores-deitadas.evaluation">
 			<title>Training and Evaluation</title>
 			    <para>
 			        To perform the evaluation the corpus was split into a training and a test part.
 			        <screen>
-			        <![CDATA[
-$ sed '1,55172d' corpus.txt > corpus_train.txt
+<![CDATA[$ sed '1,55172d' corpus.txt > corpus_train.txt
 $ sed '55172,100000000d' corpus.txt > corpus_test.txt]]>
         			</screen>
         			<screen>
-        			<![CDATA[
-$ opennlp TokenNameFinderTrainer -model pt-ner.bin -cutoff 20 -lang PT -data corpus_train.txt -encoding UTF-8
+<![CDATA[$ opennlp TokenNameFinderTrainer -model pt-ner.bin -cutoff 20 -lang PT -data corpus_train.txt -encoding UTF-8
 ...
 $ opennlp TokenNameFinderEvaluator -model pt-ner.bin -lang PT -data corpus_train.txt -encoding UTF-8
 
@@ -453,7 +442,7 @@ F-Measure: 0.7717879983140168]]>
 		</section>
 	</section>
 
-	<section id="tools.corpora.ontonotes">
+	<section xml:id="tools.corpora.ontonotes">
 		<title>OntoNotes Release 4.0</title>
 	<para>
 		"OntoNotes Release 4.0, Linguistic Data Consortium (LDC) catalog number
@@ -491,7 +480,7 @@ F-Measure: 0.7717879983140168]]>
 		over a million words each of English and Chinese, and half a million
 		words of Arabic over five years." (https://catalog.ldc.upenn.edu/LDC2011T03)
 	</para>
-		<section id="tools.corpora.ontonotes.namefinder">
+		<section xml:id="tools.corpora.ontonotes.namefinder">
 		<title>Name Finder Training</title>
 	<para>
 		The OntoNotes corpus can be used to train the Name Finder. The corpus
@@ -502,8 +491,7 @@ F-Measure: 0.7717879983140168]]>
 		<para>
 		The sample shows how to train a model to detect person names.		
 			<programlisting>
-			<![CDATA[
-$ bin/opennlp TokenNameFinderTrainer.ontonotes -lang en -model en-ontonotes.bin \
+<![CDATA[$ bin/opennlp TokenNameFinderTrainer.ontonotes -lang en -model en-ontonotes.bin \
 			 -nameTypes person -ontoNotesDir ontonotes-release-4.0/data/files/data/english/
 			 
 Indexing events using cutoff of 5
@@ -534,7 +522,7 @@ path: /dev/opennlp/trunk/opennlp-tools/en-ontonotes.bin]]>
 		</section>
 	</section>
 
-	<section id="tools.corpora.brat">
+	<section xml:id="tools.corpora.brat">
 		<title>Brat Format Support</title>
 		<para>
 			The brat annotation tool is an online environment for collaborative text annotation and
@@ -546,7 +534,7 @@ path: /dev/opennlp/trunk/opennlp-tools/en-ontonotes.bin]]>
 
 		<mediaobject>
 			<imageobject>
-				<imagedata fileref="images/brat.png" width="6.5in" depth="4in" scalefit="1"/>
+				<imagedata fileref="images/brat.png" width="5.5in" scalefit="1"/>
 			</imageobject>
 		</mediaobject>
 
@@ -554,15 +542,15 @@ path: /dev/opennlp/trunk/opennlp-tools/en-ontonotes.bin]]>
 			OpenNLP can directly be trained and evaluated on labeled data in the brat format.
 			Instructions on how to use, download and install brat can be found on the project website:
 
-			<ulink url="https://brat.nlplab.org">https://brat.nlplab.org</ulink>
+			<link xlink:href="https://brat.nlplab.org">https://brat.nlplab.org</link>
 
 			Configuration of brat, including setting up the different entities and relations can be found at:
 
-			<ulink url="https://brat.nlplab.org/configuration.html">https://brat.nlplab.org/configuration.html</ulink>
+			<link xlink:href="https://brat.nlplab.org/configuration.html">https://brat.nlplab.org/configuration.html</link>
 
 		</para>
 
-		<section id="tools.corpora.brat.training">
+		<section xml:id="tools.corpora.brat.training">
 			<title>Training</title>
 			<para>
 				To train your namefinder model using your brat annotated files you can either use the opennlp command
@@ -573,47 +561,45 @@ path: /dev/opennlp/trunk/opennlp-tools/en-ontonotes.bin]]>
 				a rule based tokenizer.
 
 				<screen>
-					<![CDATA[
-$ opennlp TokenNameFinderTrainer.brat
+<![CDATA[$ opennlp TokenNameFinderTrainer.brat
 Usage: opennlp TokenNameFinderTrainer.brat [-factory factoryName] [-resources resourcesDir] [-type modelType]
 [-featuregen featuregenFile] [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language
 -model modelFile [-tokenizerModel modelFile] [-ruleBasedTokenizer name] -annotationConfig annConfFile
 -bratDataDir bratDataDir [-recursive value] [-sentenceDetectorModel modelFile]
 
 Arguments description:
-	-factory factoryName
-		A sub-class of TokenNameFinderFactory
-	-resources resourcesDir
-		The resources directory
-	-type modelType
-		The type of the token name finder model
-	-featuregen featuregenFile
-		The feature generator descriptor file
-	-nameTypes types
-		name types to use for training
-	-sequenceCodec codec
-		sequence codec used to code name spans
-	-params paramsFile
-		training parameters file.
-	-lang language
-		language which is being processed.
-	-model modelFile
-		output model file.
-	-tokenizerModel modelFile
-	-ruleBasedTokenizer name
-	-annotationConfig annConfFile
-	-bratDataDir bratDataDir
-		location of brat data dir
-	-recursive value
-	-sentenceDetectorModel modelFile
+		-factory factoryName
+			A sub-class of TokenNameFinderFactory
+		-resources resourcesDir
+			The resources directory
+		-type modelType
+			The type of the token name finder model
+		-featuregen featuregenFile
+			The feature generator descriptor file
+		-nameTypes types
+			name types to use for training
+		-sequenceCodec codec
+			sequence codec used to code name spans
+		-params paramsFile
+			training parameters file.
+		-lang language
+			language which is being processed.
+		-model modelFile
+			output model file.
+		-tokenizerModel modelFile
+		-ruleBasedTokenizer name
+		-annotationConfig annConfFile
+		-bratDataDir bratDataDir
+			location of brat data dir
+		-recursive value
+		-sentenceDetectorModel modelFile
 ]]>
 				</screen>
 
 				The following command will train a danish organization name finder model.
 
 				<screen>
-					<![CDATA[
-$ opennlp TokenNameFinderTrainer.brat -resources conf/resources \
+<![CDATA[$ opennlp TokenNameFinderTrainer.brat -resources conf/resources \
 -featuregen conf/resources/fg-da-org.xml -nameTypes Organization \
 -params conf/resources/TrainerParams.txt -lang da \
 -model models/da-org.bin -ruleBasedTokenizer simple \
@@ -660,13 +646,12 @@ Compressed 1403655 parameters to 116378
 done (11.099s)
 
 Wrote name finder model to
-path: models/da-org.bin
-]]>
+path: models/da-org.bin]]>
 				</screen>
 			</para>
 		</section>
 
-		<section id="tools.corpora.brat.evaluation">
+		<section xml:id="tools.corpora.brat.evaluation">
 			<title>Evaluation</title>
 			<para>
 				To evaluate you name finder model opennlp provides an evaluator that works with your brat
@@ -678,8 +663,7 @@ path: models/da-org.bin
 				it should be able to identify. Shuffling the data before splitting is most likely sufficient in many cases.
 
 				<screen>
-					<![CDATA[
-$ opennlp TokenNameFinderEvaluator.brat -model models/da-org.bin \
+<![CDATA[$ opennlp TokenNameFinderEvaluator.brat -model models/da-org.bin \
 -ruleBasedTokenizer simple -annotationConfig data/annotation.conf \
 -bratDataDir data/gold/da/test -recursive true \
 -sentenceDetectorModel models/da-sent.bin
@@ -692,14 +676,12 @@ Runtime: 10.043s
 
 Precision: 0.7321974661424203
 Recall: 0.25176505933603727
-F-Measure: 0.3746926000447127
-
-]]>
+F-Measure: 0.3746926000447127]]>
 				</screen>
 			</para>
 		</section>
 
-		<section id="tools.corpora.brat.cross-validation">
+		<section xml:id="tools.corpora.brat.cross-validation">
 			<title>Cross Validation</title>
 			<para>
 				You can also use the cross validation to evaluate you model. This can come in handy when you do
@@ -707,8 +689,7 @@ F-Measure: 0.3746926000447127
 				Running cross validation with the misclassified attribute set to true can also be helpful because it
 				will identify missed annotations as they will pop up as false positives in the text output.
 				<screen>
-					<![CDATA[
-$ opennlp TokenNameFinderCrossValidator.brat -resources conf/resources \
+<![CDATA[$ opennlp TokenNameFinderCrossValidator.brat -resources conf/resources \
 -featuregen conf/resources/fg-da-org.xml -nameTypes Organization \
 -params conf/resources/TrainerParams.txt -lang da -misclassified true \
 -folds 10 -detailedF true -ruleBasedTokenizer simple -annotationConfig data/annotation.conf \
@@ -737,10 +718,7 @@ done
 
 Evaluated 26133 samples with 13053 entities; found: 12174 entities; correct: 10361.
        TOTAL: precision:   85.11%;  recall:   79.38%; F1:   82.14%.
-Organization: precision:   85.11%;  recall:   79.38%; F1:   82.14%. [target: 13053; tp: 10361; fp: 1813]
-
-
-        ]]>
+Organization: precision:   85.11%;  recall:   79.38%; F1:   82.14%. [target: 13053; tp: 10361; fp: 1813]]]>
 				</screen>
 			</para>
 		</section>
diff --git a/opennlp-docs/src/docbkx/css/opennlp-docs.css b/opennlp-docs/src/docbkx/css/opennlp-dev-manual.css
similarity index 74%
rename from opennlp-docs/src/docbkx/css/opennlp-docs.css
rename to opennlp-docs/src/docbkx/css/opennlp-dev-manual.css
index 172ee44d..920d6404 100644
--- a/opennlp-docs/src/docbkx/css/opennlp-docs.css
+++ b/opennlp-docs/src/docbkx/css/opennlp-dev-manual.css
@@ -40,7 +40,20 @@ div.book {
     margin: 0 auto;
     font-family: var(--font-family);
     padding: 1rem;
-    background-color: white;
+}
+
+div.cover {
+    text-align: center;
+    page-break-after: always;
+    padding: 0;
+    margin: 0;
+}
+
+div.cover img {
+    height: 100%;
+    max-width: 100%;
+    padding: 10px;
+    margin: 0;
 }
 
 div.toc > dl, div.list-of-tables > dl {
@@ -53,12 +66,53 @@ a {
     text-decoration: none;
 }
 
-h1, h2, h3, h4, div.toc {
+/* font plan- serif text, sans headers */
+h1, h2, h3, h4, h5, h6, div.toc {
     color: var(--red-color);
+    hyphens: none !important;
+    -moz-hyphens: none !important;
+    -webkit-hyphens: none !important;
+    adobe-hyphenate: none !important;
+    page-break-after: avoid;
+    page-break-inside: avoid;
+    text-indent: 0;
+    text-align: left;
+}
+
+h1 + p, h2 + p, h3 + p, h4 + p, h5 + p, h6 + p {
+    text-indent: 0;
+}
... 4082 lines suppressed ...