Newsgroups: comp.ai.nat-lang,comp.ai.neural-nets,comp.speech
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!udel!gatech!swrinde!cs.utexas.edu!news.sprintlink.net!alfa02.medio.net!netnews.nwnet.net!ns1.nodak.edu!isc.cs.ndsu.nodak.edu!fhusain
From: fhusain@isc.cs.ndsu.nodak.edu (Fatima Husain)
Subject: Request for information
Sender: usenet@ns1.nodak.edu (Usenet login)
Message-ID: <D4uLLx.LDq@ns1.nodak.edu>
Date: Fri, 3 Mar 1995 04:53:57 GMT
Nntp-Posting-Host: isc.cs.ndsu.nodak.edu
Organization: Intelligent Systems Cluster
Lines: 24
Xref: glinda.oz.cs.cmu.edu comp.ai.nat-lang:2975 comp.ai.neural-nets:22460 comp.speech:4853


Hello!
I am working on a layered, self-organizing neural network capable of
learning the structure of sentences and classifying unknown words.
If an NLP system has to be  reasonably general-purpose, it has to deal 
with ungrammatical sentences and unknown words. The approach we
have taken is that, once the unknown words are categorized, its easier to
parse the sentences.  
Categorization of such words can also be done by using 
stochastic-based methods using probability estimates. 

Have such studies or experiments been done? If so, could you give me
any related information? I am interested in both neural network and
non-neural network based experiments. Any leads - journal articles/
conference publications/ dissertations/books are welcome.

Thanks much!
--fatima

-- 
                                    / \ 
   Somewhere there's a place called |-|ome...
   In the meanwhile you can reach me at - fhusain@plains.nodak.edu
                                          fhusain@badlands.nodak.edu
