Reutilización de datos lingüísticos para la creación de un sistema de traducción automática para un nuevo par de lenguas

  1. Armentano Oller, Carme
  2. Forcada Zubizarreta, Mikel L.
Journal:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Year of publication: 2008

Issue: 41

Pages: 243-250

Type: Article

More publications in: Procesamiento del lenguaje natural

Abstract

This work examines various ways to re-use pre-existing linguistic data to quickly generate a machine translation system for a new language pair. In particular, a machine translation system between Portuguese and Catalan based on the Apertium platform (www.apertium.org) has been built from data existing in this platform for translating between Portuguese and Spanish and between Spanish and Catalan. The results obtained indicate that a simple composition of two complete translators is an adequate first option, but other very interesting results are shown which have been obtained in short time using the tools provided in the Apertium platform.