Improving phrase-based statistical translation by modifying phrase extraction and including several features

Abstract

Nowadays, most of the statistical translation systems are based on phrases (i.e. groups of words). In this paper we study different improvements to the standard phrase-based translation system. We describe a modified method for the phrase extraction which deals with larger phrases while keeping a reasonable number of phrases. We also propose additional features which lead to a clear improvement in the performance of the translation. We present results with the EuroParl task in the direction Spanish to English and results from the evaluation of the shared task “Exploiting Parallel Texts for Statistical Machine Translation” (ACL Workshop on Parallel Texts 2005).