[Corpora-List] POS tagger for Japanese (Amy Aisha Brown)

Jim Breen jimbreen at gmail.com
Mon Sep 16 01:06:56 UTC 2013


Amy Aisha Brown <amy-aisha.brown at open.ac.uk> asked

> This is a long shot but I am looking for a POS tagging/morphological
> analysis system for Japanese that works (well) with tweets (i.e., something
> that has been trained with social media texts).
>
> If anyone has any information about this, I would love to hear from you.

Have you tried the usual ones? I have found MeCab/Unidic to
be effective even with texts from social media. Be sure to use the
most recent version of Unidic (2.1.1), which has a vast coverage of
morphemes. I think it's more likely that the social media  jargon will be
added to that lexicon than there will be a specific one just for tweets, etc.

Jim

-- 
Jim Breen
Adjunct Snr Research Fellow, Japanese Studies Centre, Monash University

_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora



More information about the Corpora mailing list