[Corpora-List] Computational Linguistics and NLP

[Mike Maxwell]

I'm going to misuse James L. Fidelholtz's comment on the thread about Fillmore, and turn it to a
different use.  He wrote:

> On the other hand, I believe that the inherent limits of statistical approaches to NLP will only
> be able to be overcome by good old linguistic analysis of the basic corpus data (genannt
> Sitzfleisch). I think nowadays most NLP researchers recognize the need for linguistics, and vice
> versa, though perhaps closer collaboration is needed to find the proper, ideal mix of the two
> types of areal expertise.

--namely, to draw attention to an upcoming workshop at ACL on 26 June, entitled "ComputEL: The use 
of computational methods in the study of endangered languages."  The announcement is here:
    http://www.acsu.buffalo.edu/~jcgood/ComputEL.html
The workshop is more about developing computational methods that will work for documentary 
linguistics, and particularly for endangered languages, where the corpora are comparatively quite 
small (in fact, miniscule compared to the corpora of major languages).  I hope to see some of you there!
-- 
	Mike Maxwell
	maxwell at umiacs.umd.edu
	"My definition of an interesting universe is
	one that has the capacity to study itself."
         --Stephen Eastmond

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