Need to creat Lexical Resources for Indian Lang.

[M K Saravanan <mksarav@xxxxxxxxxxxxxxxxx>]

---------- Forwarded message ----------
Date: Thu, 12 Oct 2000 08:00:49 +0530 (IST)
From: M K Saravanan <mksarav@xxxxxxxxxxxxxxxxx>
To: tamilinix@xxxxxxxxxxx
Subject: Re: [tamilinix] FYI - Indic Pango, support for other Indian Languages

On Thu, 12 Oct 2000, Maniam wrote:
> Would members of this group prep to m ake a presenation on tamil linux in 
> the forth coming
> Tamil Inaiyam 2001 in Kuala Lumpur ,Malaysia

sure.  Particularly Mr.Siva & his group has done significant work on tamil
KDE.  Recently ACL (Association of COmputational Linguistics) Intl.
Conference held from Oct 3-9 at HongKong.  only one person from
India Participated in that conference (Dr.Rajeev Sangal, Lang. Technology
Research Centre, IIIT, Hyderabad).  Fortunately I had a chance to meet him
at chennai and discussed about position of Indian Lang. at International
Scenario.  He said according to the current situation India seems to
lagging behind atleast 10 years in the case of building lexical resources
like

* Building Huge Annotated Corpora for Indian Lang.
* Building Parallel Corpora for Indian Lang.
* Statistical Data Processing Tools for Indian Lang.
* Building reasobly sized dictionary/thesaurus for Indian Lang.
etc.., 
He has a strong believe in Open source for these kind of activities.  His
group (earlier at IIT-Kanpur then Central Univ. Hyderabad & now at IIIT,
Hyderabad) has developed Indian lang. to Indian lang. Human Aided Machine
Translation System called "Anusaaraka" for the following:

telugu to hindi
marathi to hindi
kannada to hindi
(all under GNU/GPL)
interested guys can watch about anusaaraka at:

http://www.tdil.gov.in/anusarakahtm.htm  (it's a old link i will update
about thenew link soon). also go thru www.tdil.gov.in

At our centre (AU-KBC) we have developed a preliminary version of Tamil to
Hindi Anusaaraka which contains 32,000 words in the dictionary.  Currently
it is in development stage and translate simple sentences (without
ambiguity). We are also planning to start English to Tamil Human aided MT
system from Nov.2000 onwards.

We (tamilinix) should make short term and long term goals atleast for the
next one year so that we can move fast.  we can even setup a translation
team for the Linux-HOWTOs.  CUrrently I am writing a small linux tutor
(for avg. level computer user) in tamil (TSCII format using AkaramTeX
editor). By this weekend i will post it to the list.  

suggestions are welcome.

-- mks --


 -- 
********************************************************************
M K Saravanan, 
Member Research Staff,
The AU-KBC Centre for Internet & Telecom Technologies,
Madras Institute of Technology, Anna University,
Chromepet, Chennai 600 044.
Tamilnadu, INDIA

Tel     (O): 91 44 2417885         Email: mksarav@xxxxxxxxxxxx
Telefax (O): 91 44 2402711         URL  : http://mksarav.tripod.com
*******************************************************************






---
Visit our home page at: www.chennailug.org
Send e-mail to 'ilugc-request@xxxxxxxxxxxxxxxxxx' with 'unsubscribe' 
in either the subject or the body to unsubscribe from this list.