论文信息 - Recent Improvements in the CMU Large Scale Chinese-English SMT System

Recent Improvements in the CMU Large Scale Chinese-English SMT System

In this paper we describe recent improvements to components and methods used in our statistical machine translation system for Chinese-English used in the January 2008 GALE evaluation. Main improvements are results of consistent data processing, larger statistical models and a POS-based word reordering approach.

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

[2] Alexander H. Waibel,et al. Training and Evaluating Error Minimization Decision Rules for Statistical Machine Translation , 2005, ParallelText@ACL.

[3] Philipp Koehn,et al. Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[4] Matthew G. Snover,et al. A Study of Translation Edit Rate with Targeted Human Annotation , 2006, AMTA.

[5] Daniel Jurafsky,et al. A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 , 2005, IJCNLP.

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

[7] Ashish Venugopal. Training and Evaluating Error Minimization Rules for Statistical Machine Translation , 2005 .

[8] Ralph Weischedel,et al. A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION , 2005 .

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

[10] Alexander H. Waibel,et al. The CMU statistical machine translation system for IWSLT 2005 , 2005, IWSLT.

[11] José B. Mariño,et al. REORDERING EXPERIMENTS FOR N-GRAM-BASED SMT , 2006, 2006 IEEE Spoken Language Technology Workshop.

[12] Ian R. Lane,et al. The UKA/CMU statistical machine translation system for IWSLT 2006 , 2006, IWSLT.