The validity of a statistical (information theoretic) approach to MT has indeed been recognized, as the authors mention, byWeaver as early as 1949. And was universally recognized as mistaken by 1950 (cf. Hutchins, MT – Past, Present, Future, Ellis Horwood, 1986, p. 30ff and references therein). The crude force of computers is not science. The paper is simply beyond the scope of COLING.
Anonymous Coling review, 1 March 1988
(Citado en "The Dawn of Statistical ASR and MT", discurso de de Fred Jelinek de aceptación del ACL Lifetime Achievement Award, documento que tú, estimado lector, deberías, sin duda, leer.)
2 comentarios:
Ya lo dijo Chomsky. El procesamiento basado en estadísticas está sobreevaluado.
La estadística apesta.
Publicar un comentario