论文信息 - NTT System Description for the WMT2006 Shared Task

NTT System Description for the WMT2006 Shared Task

We present two translation systems experimented for the shared-task of "Workshop on Statistical Machine Translation," a phrase-based model and a hierarchical phrase-based model. The former uses a phrasal unit for translation, whereas the latter is conceptualized as a synchronous-CFG in which phrases are hierarchically combined using non-terminals. Experiments showed that the hierarchical phrase-based model performed very comparable to the phrase-based model. We also report a phrase/rule extraction technique differentiating tokenization of corpora.

[1] Daniel Marcu,et al. Statistical Phrase-Based Translation , 2003, NAACL.

[2] Taro Watanabe,et al. Left-to-Right Target Generation for Hierarchical Phrase-Based Translation , 2006, ACL.

[3] Alfred V. Aho,et al. Syntax Directed Translations and the Pushdown Assembler , 1969, J. Comput. Syst. Sci..

[4] Hermann Ney,et al. A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[5] Alexander M. Fraser,et al. A Smorgasbord of Features for Statistical Machine Translation , 2004, NAACL.

[6] Hermann Ney,et al. Discriminative Training and Maximum Entropy Models for Statistical Machine Translation , 2002, ACL.

[7] Franz Josef Och,et al. Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[8] David Chiang,et al. A Hierarchical Phrase-Based Model for Statistical Machine Translation , 2005, ACL.

[9] Hermann Ney,et al. Alignment templates: the RWTH SMT system , 2004, IWSLT.

[10] Hermann Ney,et al. The Alignment Template Approach to Statistical Machine Translation , 2004, CL.