Hi Lance,
(12/07/05 9:24), Lance Norskog wrote:
The sourceforge model site only includes European languages. Are any
of the OpenNLP algorithms useful in other language families? I'm sure
this is a large research area! I am just asking for concrete opinions.
As now I'm a grad student who just started to study NLP [1][2], I'm curious
about that, too!
A concrete thing I just learned is that parsing (syntactic tree) is not
suitable for Japanese.
"Dependency structure between bunsetsu (segment)" is used more often than the
syntactic tree
as representation of Japanese syntactic structure, the fact I've learned.
Anyway, I'd like to contribute code (especially for Japanese, I expect) to the
community
in the near future.
koji
[1] Starting Lab Work
http://soleami.com/blog/starting-lab-work.html
[2] Two Starts – JAIST and Twitter
http://soleami.com/blog/two-starts-jaist-and-twitter.html
--
http://soleami.com/blog/starting-lab-work.html
