Inducing a multilingual dictionary from a parallel multitext in related languages

Abstract

Dictionaries and word translation models are used by a variety of systems, especially in machine translation. We build a multilingual dictionary induction system for a family of related resource-poor languages. We assume only the presence of a single medium-length multitext (the Bible). The techniques rely upon lexical and syntactic similarity of languages as well as on the fact that building dictionaries for several pairs of languages provides information about other pairs. © 2005 Association for Computational Linguistics.