James L. Fidelholtz e-mail: jfidel@siu.buap.mx
Maestría en Ciencias del Lenguaje
Instituto de Ciencias Sociales y Humanidades
Benemérita Universidad Autónoma de Puebla, MÉXICO
-------------------------------------------------------------------------
[From the LINGUIST List: Vol-10-1921][beginning of message]
Date: Fri, 10 Dec 1999 01:51:21 PST
From: "Niladri Sekhar Dash" <niladrisekhar@hotmail.com>
Subject: NLP
In my recent research in NLP, from a written corpus of Bangla, I have
accumulated a huge number of surface wordforms, which are ambiguous
both in form and function. These forms posit great problem for
morphological processing, parts-of-speech tagging and other related
works. For disambiguation, I have applied a few methods such as
lexical association, probabilty measure, internal structure of the
wordfrom, contexual occurrence etc., but the result is not
satisfactory. Hence, I would earnestly request the experts in this
area to guide me. I would be grateful if anybody can give me the
information if any work is done in this area or if any
article/book/journal etc. is available for the purpose.
I convey my thanks in advance.
The summary would be posted in the LINGUIST LIST [Note from JLF: I'm
sure he'll post it here, too, after he gets this message.]
With kind regards,
Niladri Sekhar Dash
Computer Vision and Pattern Recognition Unit
Indian Statistical Institute
203, B.T. Road
Calcutta - 700 035.
mail: <niladri@isical.ac.in> (Off) <niladrisekhar@hotmail.com> (Res)
[end of message]