You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@opennlp.apache.org by "William Colen (Created) (JIRA)" <ji...@apache.org> on 2012/02/04 02:47:53 UTC
[jira] [Created] (OPENNLP-423) Improve Portuguese NameSample and
ChunkSample formaters
Improve Portuguese NameSample and ChunkSample formaters
-------------------------------------------------------
Key: OPENNLP-423
URL: https://issues.apache.org/jira/browse/OPENNLP-423
Project: OpenNLP
Issue Type: Improvement
Reporter: William Colen
Assignee: William Colen
Priority: Minor
I found some issues with the Portuguese NameSample and ChunkSample formaters.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Closed] (OPENNLP-423) Improve Portuguese NameSample and
ChunkSample formatters
Posted by "William Colen (Closed) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/OPENNLP-423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
William Colen closed OPENNLP-423.
---------------------------------
Resolution: Fixed
Fixed. Now the evaluation results are:
NameFinder (amazonia.ad):
Evaluated 275769 samples with 325409 entities; found: 301643 entities; correct: 245105.
TOTAL: precision: 81.26%; recall: 75.32%; F1: 78.18%.
time: precision: 91.97%; recall: 90.01%; F1: 90.98%. [target: 18197; tp: 16380; fp: 1430]
numeric: precision: 89.82%; recall: 84.15%; F1: 86.89%. [target: 15157; tp: 12755; fp: 1446]
event: precision: 90.58%; recall: 78.96%; F1: 84.37%. [target: 49994; tp: 39475; fp: 4107]
place: precision: 83.88%; recall: 79.49%; F1: 81.63%. [target: 51669; tp: 41071; fp: 7892]
person: precision: 77.32%; recall: 78.85%; F1: 78.07%. [target: 83770; tp: 66050; fp: 19377]
organization: precision: 76.21%; recall: 72.24%; F1: 74.17%. [target: 69190; tp: 49986; fp: 15604]
thing: precision: 80.24%; recall: 55.11%; F1: 65.35%. [target: 9905; tp: 5459; fp: 1344]
abstract: precision: 74.02%; recall: 55.89%; F1: 63.69%. [target: 11050; tp: 6176; fp: 2168]
artprod: precision: 70.98%; recall: 47.05%; F1: 56.59%. [target: 16477; tp: 7753; fp: 3170]
Chunker (Bosque_CF_8.0.ad.txt):
Evaluated 4212 samples with 48628 entities; found: 48534 entities; correct: 44314.
TOTAL: precision: 91.31%; recall: 91.13%; F1: 91.22%.
PP: precision: 95.20%; recall: 94.35%; F1: 94.77%. [target: 12645; tp: 11931; fp: 602]
VP: precision: 92.57%; recall: 92.93%; F1: 92.75%. [target: 8244; tp: 7661; fp: 615]
NP: precision: 89.25%; recall: 89.15%; F1: 89.20%. [target: 25362; tp: 22610; fp: 2723]
ADVP: precision: 88.29%; recall: 88.85%; F1: 88.57%. [target: 2377; tp: 2112; fp: 280]
> Improve Portuguese NameSample and ChunkSample formatters
> --------------------------------------------------------
>
> Key: OPENNLP-423
> URL: https://issues.apache.org/jira/browse/OPENNLP-423
> Project: OpenNLP
> Issue Type: Improvement
> Components: Formats
> Affects Versions: tools-1.5.3-incubating
> Reporter: William Colen
> Assignee: William Colen
> Priority: Minor
> Fix For: tools-1.5.3-incubating
>
>
> I found some issues with the Portuguese NameSample and ChunkSample formaters.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (OPENNLP-423) Improve Portuguese NameSample and
ChunkSample formatters
Posted by "William Colen (Updated) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/OPENNLP-423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
William Colen updated OPENNLP-423:
----------------------------------
Component/s: Formats
Affects Version/s: tools-1.5.3-incubating
Fix Version/s: tools-1.5.3-incubating
Summary: Improve Portuguese NameSample and ChunkSample formatters (was: Improve Portuguese NameSample and ChunkSample formaters)
> Improve Portuguese NameSample and ChunkSample formatters
> --------------------------------------------------------
>
> Key: OPENNLP-423
> URL: https://issues.apache.org/jira/browse/OPENNLP-423
> Project: OpenNLP
> Issue Type: Improvement
> Components: Formats
> Affects Versions: tools-1.5.3-incubating
> Reporter: William Colen
> Assignee: William Colen
> Priority: Minor
> Fix For: tools-1.5.3-incubating
>
>
> I found some issues with the Portuguese NameSample and ChunkSample formaters.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira