论文信息 - Phrase Table Combination Deficiency Analyses in Pivot-Based SMT

Phrase Table Combination Deficiency Analyses in Pivot-Based SMT

As the parallel corpus is not available all the time, pivot language was introduced to solve the parallel corpus sparseness in statistical machine translation. In this paper, we carried out several phrase-based SMT experiments, and analyzed the detailed reasons that caused the decline in translation performance. Experimental results indicated that both covering rate of phrase pairs and translation probability accuracy affect the quality of translation.

Tiejun Zhao | Conghui Zhu | Dequan Zheng | Yiming Cui | Xiaoning Zhu

[1] Hitoshi Isahara,et al. A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation , 2007, NAACL.

[2] Tiejun Zhao,et al. Construct Trilingual Parallel Corpus on Demand , 2006, ISCSLP.

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

[4] Mirella Lapata,et al. Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora , 2007, ACL.

[5] Eiichiro Sumita,et al. Translation Quality Indicators for Pivot-based Statistical MT , 2011, IJCNLP.

[6] Qiang Huo. Chinese Spoken Language Processing, 5th International Symposium, ISCSLP 2006, Singapore, December 13-16, 2006, Proceedings , 2006, ISCSLP.

[7] Hua Wu,et al. Pivot language approach for phrase-based statistical machine translation , 2007, ACL.

[8] A. Gispert,et al. Catalan-English Statistical Machine Translation without Parallel Corpus : Bridging through Spanish , 2006 .