Constraining a Generative Word Alignment Model with Discriminative Output

被引:1
作者
Goh, Chooi-Ling [1 ]
Watanabe, Taro [1 ]
Yamamoto, Hirofumi [1 ]
Sumita, Eiichiro [1 ]
机构
[1] Natl Inst Informat & Commun Technol, Keihanna Sci City, Kyoto Fu 6190289, Japan
关键词
word alignment; discriminative model; generative model; hybrid; SMT;
D O I
10.1587/transinf.E93.D.1976
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present a method to constrain a statistical generative word alignment model with the output from a discriminative model. The discriminative model is trained using a small set of hand-aligned data that ensures higher precision in alignment. On the other hand, the generative model improves the recall of alignment. By combining these two models, the alignment output becomes more suitable for use in developing a translation model for a phrase-based statistical machine translation (SMT) system. Our experimental results show that the joint alignment model improves the translation performance. The improvement in average of BLEU and METEOR scores is around 1.0-3.9 points.
引用
收藏
页码:1976 / 1983
页数:8
相关论文
共 17 条
[11]  
Fraser Alexander., 2007, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), P51
[12]   Comparative study on corpora for speech translation [J].
Kikui, Genichiro ;
Yamamoto, Seiichi ;
Takezawa, Toshiyuki ;
Sumita, Eiichiro .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (05) :1674-1682
[13]  
Lacoste-Julien S., 2006, Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, P112
[14]  
Liang Percy, 2006, Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, P104, DOI [DOI 10.3115/1220835.1220849, 10.3115/1220835.1220849]
[15]  
Moore R.C., 2005, P C HUMAN LANGUAGE T, P81
[16]  
Och FJ, 2003, COMPUT LINGUIST, V29, pc, DOI 10.1162/089120103321337421
[17]  
[赵红梅 ZHAO Hongmei], 2009, [中文信息学报, Journal of Chinese Information Processing], V23, P65