>
> Will anyone be so kind to tell me the source for the division of the
> three different levels of machine translation? As far as I know,
> it was proposed by E.Nida, which includes MT based on theorectical
> linguistics, based on communication theory, and based on social
> linguistics, etc. I'd like to make reference to the paper or article.
> I really appreciat the help from whom can provide me with the
> source of idea.
>
In the early fifties, Zellig Harris introduced a notion of "transfer
grammar" that, as far as I can tell, was the source for the notion of
transfer in machine translation.
Harris Z., Transfer Grammar, International Journal of American
Linguistics, 20:4, 1954, 259-270.
As for the "transfer architecture" in MT
(analysis/transfer/generation), I believe it was introduced in a great
paper written by Victor Yngve:
Yngve, V., A Framework for Syntactic Translation, Mechanical
Translation, 4:3, 1957, 59-65.
-- Pierre Isabelle, RALI, DIRO Universite de Montreal, C.P. 6128, Succ. Centre-Ville Montreal, Quebec, Canada H3C 3J7 tel: (514) 343-6161 fax: (514) 343-2496 e-mail: isabelle@iro.umontreal.ca W3: http://www-rali.iro.umontreal.ca