Abstract

We propose a novel reordering model for phrase-based statistical machine translation (SMT) that uses a maximum entropy (MaxEnt) model to predicate reorderings of neighbor blocks (phrase pairs). The model provides content-dependent, hierarchical phrasal reordering with generalization based on features automatically learned from a real-world bitext. We present an algorithm to extract all reordering events of neighbor blocks from bilingual data. In our experiments on Chineseto-English translation, this MaxEnt-based reordering model obtains significant improvements in BLEU score on the NIST MT-05 and IWSLT-04 tasks. 1

Citations

417	Statistical phrase-based translation - Koehn, Och, et al. - 2003
343	Stochastic inversion transduction grammars and bilingual parsing of parallel corpora - Wu - 1997
341	Improved statistical alignment models - Och, Ney - 2000
257	A hierarchical phrase-based model for statistical machine translation - Chiang - 2005
245	The alignment template approach to statistical machine translation - Och, Ney - 2004
171	A comparison of algorithms for maximum entropy parameter estimation - Malouf - 2002
103	Better k-best parsing - Huang, Chiang - 2005
84	Decoding complexity in wordreplacement translation models - Knight - 1999
68	A polynomial-time algorithm for statistical machine translation - Wu - 1996
28	Local phrase reordering models for statistical machine translation - Kumar, Byrne - 2005
20	A block orientation model for statistical machine translation - Tillmann - 2004
15	A localized prediction model for statistical machine translation - Tillmann, Zhang - 2005
14	Considerations in maximum mutual information and minimum classification error training for statistical machine translation - Venugopal, Vogel - 2005
8	Reordering constraints for phrase-based statistical machine translation - Zens, Ney, et al. - 2004
5	System Description for the 2005 IWSLT Speech Translation Evaluation - Edinburgh - 2005
4	Minimum error rate training in statistical machine translation - 2003a
2	Statistical Machine Translation: From Single-Word Models to Alignment Templates Thesis - 2003b
2	C4.5: progarms for machine learning - Quinlan - 1993