论文信息 - NTT SMT System 2008 at NTCIR-7

NTT SMT System 2008 at NTCIR-7

This paper describes NTT SMT System 2008 presented at the patent translation task (PAT-MT) in NTCIR-7. For PAT-MT, we submitted our strong baseline system faithfully following a hierarchical phrasebased statistical machine translation [2]. The hierarchical phrase-based SMT is based on a synchronousCFGs in which a paired source/target rules are synchronously applied starting from the initial symbol. The decoding is realized by a CYK-style bottom-up parsing on the source side with each derivation representing a translation candidate. We demonstrate the strong baseline for the PAT-MT English/Japanese translations.

[1] David Chiang,et al. Forest Rescoring: Faster Decoding with Integrated Language Models , 2007, ACL.

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

[3] Hermann Ney,et al. HMM-Based Word Alignment in Statistical Translation , 1996, COLING.

[4] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[5] Taro Watanabe,et al. NTT statistical machine translation system for IWSLT 2008 , 2008, IWSLT.

[6] Stephan Vogel,et al. An Efficient Two-Pass Approach to Synchronous-CFG Driven Statistical MT , 2007, NAACL.

[7] Masaaki Nagata,et al. NUT-NTT Statistical Machine Translation System for IWSLT 2005 , 2005, IWSLT.

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

[9] David Chiang,et al. Hierarchical Phrase-Based Translation , 2007, CL.

[10] Taro Watanabe,et al. NTT System Description for the WMT2006 Shared Task , 2006, WMT@HLT-NAACL.

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

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

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