Handling Multi-word Expressions Without Explicit Linguistic Rules in an MT System

Abstract

Translation of Multi-word expressions (MWEs) is one of the most challenging tasks of a Machine translation (MT) system. In this paper, we present an innovative technique for dealing with MWEs in the context of MT. The technique permits bilinguals to give translations of MWEs in the form of patterns, without requiring them to be trained linguistically. The interpretation of the patterns is done by a dynamic machine learning algorithm, which allows the main rule-based MT system to operate based on linguistic rules. Thus, the bilingual patterns (without any explicit linguistic input) are used in conjunction with the main linguistic system. This is made possible by the learning pathway templates. These templates need to be specially prepared by trained linguists only once. After that they help to process potentially a large number of patterns.The implemented system is being used with a large-scale rule-based MT system to improve its performance. This framework can also be extended to help example-based or statistical MT systems to deal with MWEs.KeywordsMachine TranslationTarget LanguageInput SentenceLexical CategoryActual SentenceThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.