[
https://issues.apache.org/jira/browse/TIKA-5052?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18139794#comment-18139794
]
Tim Allison commented on TIKA-5052:
-----------------------------------
The numbers actually look too good to be true to me.
I'll see what happens on the 1.2 million corpora run. The above numbers include
the full chain including the updated junk detector.
> Update encoding detector
> ------------------------
>
> Key: TIKA-5052
> URL: https://issues.apache.org/jira/browse/TIKA-5052
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Major
>
> The recent Arabic ISO issue encouraged me to look again at mojibuster. I've
> spent the last few days curating and improving a train/dev/test corpus
> derived largely from [~jnioche]'s common-crawl html contribution back in
> January 2024(?). The corpus is heavily oversampled for non-ascii and is a
> treasure trove.
> Along the way, I experimented with a hashed byte ngram model, and it seems to
> work much better so far than the earlier naive bayes approach. This model
> also incorporates UTF16 rather than adjudicating a side car wide unicode
> classifier.
> I'll continue to have bots tagging the original html corpus and supplement it
> with other datasets to make training and evaluating new models easier.
> Initial results with a cnn model were promising, but a bit slow without jdk25
> vectorization. I'll likely keep working on that.
> And, of course, we can add more charsets as needed: DOS and ebcdic maybe?
--
This message was sent by Atlassian Jira
(v10.3.26#10030026)
