[
https://issues.apache.org/jira/browse/TIKA-4719?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Tim Allison updated TIKA-4719:
------------------------------
Summary: (largely) Language agnostic junk detector (was: Language agnostic
junk detector)
> (largely) Language agnostic junk detector
> -----------------------------------------
>
> Key: TIKA-4719
> URL: https://issues.apache.org/jira/browse/TIKA-4719
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Major
>
> We struggled with short strings in our two stage lang id->lang modeling.
> Let's pull back and thing of something more general.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
