论文信息 - The NiCT-ATR statistical machine translation system for IWSLT 2006

The NiCT-ATR statistical machine translation system for IWSLT 2006

This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and IE) and all two tracks (OPEN and CSTAR). We used a phrase-based SMT in the OPEN track and a hybrid multiple translation engine in the CSTAR track. We also equipped our system with some of new preprocessing and post-processing techniques for Chinese word segmentation, named entity translation, punctuation and capitalization, sentence splitting, and language model adaptation. Our experiments show these features significantly improved our system.

[1] Eiichiro Sumita,et al. Nobody is perfect: ATR’s hybrid approach to spoken language translation , 2005, IWSLT.

[2] H. Keselman,et al. Multiple Comparison Procedures , 2005 .

[3] Taro Watanabe,et al. Using Language and Translation Models to Select the Best among Outputs from Multiple MT Systems , 2002, COLING.

[4] Nizar Habash,et al. Permission is granted to quote short excerpts and to reproduce figures and tables from this report, provided that the source of such material is fully acknowledged. Arabic Preprocessing Schemes for Statistical Machine Translation , 2006 .

[5] Treebank Penn,et al. Linguistic Data Consortium , 1999 .

[6] Hermann Ney,et al. The RWTH statistical machine translation system for the IWSLT 2006 evaluation , 2006, IWSLT.

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

[8] Eiichiro Sumita,et al. Subword-based Tagging by Conditional Random Fields for Chinese Word Segmentation , 2006, NAACL.

[9] E. Sumita,et al. Practical Approach to Syntax-based Statistical Machine Translation , 2005, MTSUMMIT.

[10] A. Tamhane,et al. Multiple Comparison Procedures , 1989 .