Statistical Machine Translation based on LDA

Current Statistical Machine Translation (SMT) systems translate one sentence at a time, ignoring any document level information. Consequently, translation models are learned only at sentence level and document contexts are generally overlooked. In this paper, we try to introduce document topic to help SMT system to produce target sentences. First, the parallel training corpus with underlying document boundary is segmented into multiple documents, and then we use a monolingual LDA model to determine which topics these documents belong to. Next, the background phrase table is enhanced with the probability distribution of a document over topics. Evaluation shows that our proposed approach significantly improves the BLEU score on Chinese-to-English machine translation.