Enhancing a Rule-Based MT System with Cross-Lingual WSD

Abstract

Lexical ambiguity is a significant problem facing rule-based machine translation systems, as many words have several possible translations in a given target language, each of which can be considered a sense of the word from the source language. The difficulty of resolving these ambiguities is mitigated for statistical machine translation systems for language pairs with large bilingual corpora, as large n-gram language models and phrase tables containing common multi-word expressions can encourage coherent word choices.
For most language pairs these resources are not available, so a primarily rule-based approach becomes attractive. In cases where some training data is available, though, we can investigate hybrid RBMT and machine learning approaches, leveraging small and potentially growing bilingual corpora. In this paper we describe the integration of statistical cross-lingual word-sense disambiguation software with SQUOIA, an existing rule-based MT system for the Spanish-Quechua language pair, and show how it allows us to learn from the available bitext to make better lexical choices, with very few code changes to the base system. We also describe Chipa, the new open source CL-WSD software used for these experiments.