Using a Bilingual Context in Word-Based Statistical Machine Translation

Abstract

Abstract. In statistical machine translation, phrase-based translation (PBT) models lead to a significantly better translation quality over single-word-based (SWB) models. PBT models translate whole phrases, thus considering the context in which a word occurs. In this work, we propose a model which further extends this context beyond phrase boundaries. The model is compared to a PBT model on the IWSLT 2007 corpus. To profit from the respective advantages of both models, we use a model combination, which results in an improvement in translation quality on the examined corpus.