At 16:53 +0900 1/07/00, Michael Cribb wrote:
>Hello all,
>
>Many thanks to the people who answered my request for references to
>statistical MT. All were useful.
>
>I'm in the last stages of preparing a paper for a journal on MT and the
>editor has asked me to explain why German-English translations using the
>SYSTRAN AltaVista translator produce poorer output compared to say
>French-English. Does anybody have any insight in to why this is so? Is it
>mainly because of a mis-match between the two languages or have the SYSTRAN
>engineers /linguists spent more time on translation between other language
>pairs?
>
>Once again, thanks in advance for your comments.
>
>Mike Cribb
>Kansai Gaidai Univ, Japan
>[EMAIL PROTECTED]
>
>
>--
> For MT-List info, see http://www.eamt.org/mt-list.html
- Less investment in G-E than in F-E
- F & E are really very near structurally and lexically
- German as a source language has to be really analyzed into a complete
sentence or utterance descriptor to obtain adequate results into almost all
target languages (surface processing might be enough for structurally very
parallel languages).
CB
-------------------------------------------------------------------------
Christian Boitet
(Pr. Universite' Joseph Fourier) Tel: +33.4-7651-4355/4817
GETA, CLIPS, IMAG-campus, BP53 Fax: +33.4-7651-4405
385, rue de la Bibliothe`que Mel: [EMAIL PROTECTED]
38041 Grenoble Cedex 9, France Mobile: +33-(0)6-6005-1969
http://www-clips.imag.fr/geta/christian.boitet
-------------------------------------------------------------------------
Projet C-STAR (http://www.c-star.org/) et projet europ�en
Nespole (http://nespole.itc.it) de traduction de parole
Projet UNL de communication et recherche d'information multilingue sur le
r�seau http://www.unl.ias.unu.edu ou http://www.unl.org
--
For MT-List info, see http://www.eamt.org/mt-list.html
