[Corpora-List] Ukrainian tagger release
Natalia Kotsyba
gnatko at gmail.com
Thu Feb 17 22:49:35 UTC 2011
To all those interested in tools for Ukrainian --
a console version of UGTag, morphosyntactic analyzer and tagger for
Ukrainian language, is now available at
https://sourceforge.net/projects/ugtag/.
The program comes with a dictionary counting over 15 thousand most
frequetly used lemmas with all their forms -- over 200 thousand unique
wordforms with about 300 thousand morphosyntactic interpretations.
The description of the tagset can be found here:
http://nl.ijs.si/ME/V4/msd/html/msd-uk.html
Disambiguation is not supported in this version but is one of the
priorities for development.
Any feedback is welcome. Please, use the sourceforge site for it.
Best regards,
Natalia Kotsyba.
_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora
More information about the Corpora
mailing list