At 17:25 06/10/99 -0400, [EMAIL PROTECTED] wrote:
>Hello all,
>I'd like to know what's the best way to develop a machine translation
>program for a language for which there are still no such translation
>tools. The goal is to make it translatable to several languages.
Well, the "best" approach is a subjective issue. Yet, the
Example-Based MT approach (EBMT) is quite adaptable to rapid-
development and rapid-deployment situations for languages that
currently have no system, and even for those that have little
electronic data available. I have co-authored several papers on this
over the past few years with colleagues at the Center for Machine
Translation/Language Technologies Institute of Carnegie Mellon
University. Papers have been presented at COLING, LREC,
AMTA, and other conferences. Christopher Hogan and my paper
presented at LREC98 is a good example of showing how fast a
usable EBMT corpus can be created with our algorithm called
TEXT-R.
Contact me off-line if you want the bibliography.
Also contact Bob Frederking at [EMAIL PROTECTED]
for more information and take a look at:
www.lti.cs.cmu.edu/Research/Diplomat
Recent news is that Ralf Brown ([EMAIL PROTECTED]) has just
started up a new Example-Based MT project. I don't have the
exact URL, but I recently saw it described under "Projects"
at www.lti.cs.cmu.edu
The CRL at New Mexico State University is also doing
quite a bit of research on this. Contact Sergei Nirenberg at
[EMAIL PROTECTED]
Isn't Ed Hovy's team at the ISI doing some work on EBMT?
contact him at <[EMAIL PROTECTED]>
>It would be necessary to start from scratch, or could it be possible
>to take advantage of an already-made multilingual system, adding our
>module to it or so...
Multi-engine MT has been going at the LTI of CMU for a few years with
the Diplomat project. See the URL above for that. There is even a paper
on it at the website. An updated paper on Evaluation of Multi-engine
MT by Christopher Hogan and Bob Frederking appeared in the
proceedings of AMTA98 (MT and the Information Soup) pp. 113 ff.
Best,
Jeff
=================================================
Jeff ALLEN - Technical Manager/Directeur Technique
European Language Resources Association (ELRA) &
European Language resources - Distribution Agency (ELDA)
(Agence Europe'enne de Distribution des Ressources Linguistiques)
55, rue Brillat-Savarin
75013 Paris FRANCE
Tel: (+33) 1.43.13.33.33 - Fax: (+33) 1.43.13.33.30
mailto:[EMAIL PROTECTED]
http://www.icp.grenet.fr/ELRA/home.html
--
For MT-List info, see http://www.eamt.org/mt-list.html
