论文信息 - NRC‘s PORTAGE System for WMT 2007

NRC‘s PORTAGE System for WMT 2007

We present the PORTAGE statistical machine translation system which participated in the shared task of the ACL 2007 Second Workshop on Statistical Machine Translation. The focus of this description is on improvements which were incorporated into the system over the last year. These include adapted language models, phrase table pruning, an IBM1-based decoder feature, and rescoring with posterior probabilities.

[1] Robert L. Mercer,et al. The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[2] Andreas Stolcke,et al. SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

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

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

[5] Truecasing For The Portage System , 2005 .

[6] Roland Kuhn,et al. Phrasetable Smoothing for Statistical Machine Translation , 2006, EMNLP.

[7] Hermann Ney,et al. N-Gram Posterior Probabilities for Statistical Machine Translation , 2006, WMT@HLT-NAACL.

[8] Roland Kuhn,et al. PORTAGE: with Smoothed Phrase Tables and Segment Choice Models , 2006, WMT@HLT-NAACL.

[9] Hermann Ney,et al. Word-Level Confidence Estimation for Machine Translation , 2007, CL.

[10] Roland Kuhn,et al. Rule-Based Translation with Statistical Phrase-Based Post-Editing , 2007, WMT@ACL.

[11] Joel D. Martin,et al. Improving Translation Quality by Discarding Most of the Phrasetable , 2007, EMNLP.