Backward and trigger-based language models for statistical machine translation. (24th July 2013)

• Record Type: Journal Article
• Authors: XIONG, DEYI; ZHANG, MIN
• Is Part Of: Natural language engineering. Volume 21:Part 2(2015)
• Page Start: 201
• Page End: 226
• Publication Date: 2013-07-24
• Subjects: Natural language processing (Computer science) -- Periodicals; Software engineering -- Periodicals; 006.35
• DOI: 10.1017/S1351324913000168
• Languages: English
• ISSNs: 1351-3249

Abstract

Abstract: The language model is one of the most important knowledge sources for statistical machine translation. In this article, we present two extensions to standard n -gram language models in statistical machine translation: a backward language model that augments the conventional forward language model, and a mutual information trigger model which captures long-distance dependencies that go beyond the scope of standard n -gram language models. We introduce algorithms to integrate the two proposed models into two kinds of state-of-the-art phrase-based decoders. Our experimental results on Chinese/Spanish/Vietnamese-to-English show that both models are able to significantly improve translation quality in terms of BLEU and METEOR over a competitive baseline.