Abstract

In this paper we describe a decoder for statistical machine translation which allows controlled reordering of the words generated in the target language. After a general discussion of the structure of a decoder a particular implementation is discussed which allows for word-toword and phrase-to-phrase translation. Word reordering is used to improve the translation quality. We analyze the effect of the length of this reordering window on the search space and the translation quality. Results for Chinese-to-English and Arabic-to-English translation tasks are presented. 1.

Citations

343	Stochastic inversion transduction grammars and bilingual parsing of parallel corpora - Wu - 1997
135	A phrase-based, joint probability model for statistical machine translation - Marcu, Wong - 2002
41	Language translation apparatus and method using context-based translation models - Berger, Brown, et al. - 1996
10	Wei-Jing Zhu, “Bleu: a method for automatic evaluation of machine translation - Papineni, Roukos, et al. - 2002
10	HMM-Based Word Alignment - Vogel, Ney, et al. - 1996
6	Integrated Phrase Segmentation and Alignment Model for Statistical Machine Translation. Submitted to - Zhang, Vogel, et al. - 2003
2	A Comparative Study on Reordering - Zens, Ney - 2003
1	evaluation kit version 9. http://www.nist.gov/speech/tests/mt - MT
1	Ney and Christoph Tillmann, A DP Search Algorithm for - Niessen, Vogel, et al. - 1998