论文信息 - A Phrase-Based,Joint Probability Model for Statistical Machine Translation

A Phrase-Based,Joint Probability Model for Statistical Machine Translation

We present a joint probability model for statistical machine translation, which automatically learns word and phrase equivalents from bilingual corpora. Translations produced with parameters estimated using the joint model are more accurate than translations produced using IBM Model 4.

Daniel Marcu | Daniel Wong | D. Marcu | Daniel Wong

[1] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

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

[3] Ronald Rosenfeld,et al. Statistical language modeling using the CMU-cambridge toolkit , 1997, EUROSPEECH.

[4] Hermann Ney,et al. Improved Alignment Models for Statistical Machine Translation , 1999, EMNLP.

[5] Kevin Knight,et al. A Syntax-based Statistical Translation Model , 2001, ACL.

[6] Daniel Marcu,et al. Towards a Unified Approach to Memory- and Statistical-Based Machine Translation , 2001, ACL.

[7] Mitchell Marcus,et al. Empirical Methods for Exploiting Parallel Texts , 2001 .

[8] Daniel Marcu,et al. Fast Decoding and Optimal Decoding for Machine Translation , 2001, ACL.

[9] Florence Reeder,et al. Corpus-based comprehensive and diagnostic MT evaluation: initial Arabic, Chinese, French, and Spanish results , 2002 .

[10] Fei Xia,et al. A Phrase-based Unigram Model for Statistical Machine Translation , 2003, HLT-NAACL.

[11] Alex Waibel,et al. The CMU statistical machine translation system , 2003, MTSUMMIT.