You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@tika.apache.org by "Kenneth William Krugler (Jira)" <ji...@apache.org> on 2020/07/27 14:21:01 UTC
[jira] [Commented] (TIKA-3147) String punctuation in lang id
component within tika-eval
[ https://issues.apache.org/jira/browse/TIKA-3147?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17165745#comment-17165745 ]
Kenneth William Krugler commented on TIKA-3147:
-----------------------------------------------
Hi [~tallison] - can you include the exact string you used (with semi-colons) that caused the language identification issue?
> String punctuation in lang id component within tika-eval
> --------------------------------------------------------
>
> Key: TIKA-3147
> URL: https://issues.apache.org/jira/browse/TIKA-3147
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Major
>
> I noticed that "the quick brown fox jumped over the lazy dog" was identified as English in tika-eval. However, if I added semi-colons, it was identified as Chinese.
> This is in alignment with what I've recently seen on a new batch of technical documents that are mostly numbers and abbreviations...these are being identified as Chinese.
> Ideally, we'd strip out punctuation while building the models, and while running language id.
> As a short term fix, we should at least strip out punctuation during detection.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)