You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@opennlp.apache.org by "Jeff Zemerick (JIRA)" <ji...@apache.org> on 2018/04/03 22:19:00 UTC
[jira] [Commented] (OPENNLP-1181) Custom NER model identifying
unwanted entities that never taught.
[ https://issues.apache.org/jira/browse/OPENNLP-1181?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16424691#comment-16424691 ]
Jeff Zemerick commented on OPENNLP-1181:
----------------------------------------
This is best posed as a question on the [users mailing list|https://opennlp.apache.org/mailing-lists.html].
> Custom NER model identifying unwanted entities that never taught.
> -----------------------------------------------------------------
>
> Key: OPENNLP-1181
> URL: https://issues.apache.org/jira/browse/OPENNLP-1181
> Project: OpenNLP
> Issue Type: Bug
> Affects Versions: 1.8.0
> Environment: Ubuntu 14.04 LTS
> Java 8
> Reporter: Mubarak K
> Priority: Minor
>
> I am new to openNLP and I trained a custom NER model with more than a million sentences using the training API of OpenNlp for identifying the skill that I taught.
> During the testing I have found that the model identifying unwanted entities that never taught.
> I want to identify only the words that I taught.
> How can improve my custom model for above mentioned result?
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)