You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@ctakes.apache.org by "ASF subversion and git services (JIRA)" <ji...@apache.org> on 2013/06/14 17:51:20 UTC
[jira] [Commented] (CTAKES-25) retrain rest of models using OpenNLP
1.5
[ https://issues.apache.org/jira/browse/CTAKES-25?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13683462#comment-13683462 ]
ASF subversion and git services commented on CTAKES-25:
-------------------------------------------------------
Commit 1493131 from james-masanz@apache.org
[ https://svn.apache.org/r1493131 ]
Part of CTAKES-25 - Sentence detector model has now been trained with OpenNLP 1.5 and saved as .bin
Trained using iters=100, cutoff-4 (see JAMIA paper)
> retrain rest of models using OpenNLP 1.5
> ----------------------------------------
>
> Key: CTAKES-25
> URL: https://issues.apache.org/jira/browse/CTAKES-25
> Project: cTAKES
> Issue Type: Improvement
> Components: ctakes-chunker, ctakes-core
> Affects Versions: 3.0-incubating
> Reporter: Pei Chen
> Assignee: James Joseph Masanz
> Fix For: 3.1
>
>
> Now that OpenNLP 1.5 is being used, should retrain the models at some point using OpenNLP 1.5 code.
> note the POS tagger was trained using OpenNLP 1.5
> but the sentence detector, chunker, and others were not retrained.
> --------------------------------------------------------------------------------
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira