计算机科学 ›› 2014, Vol. 41 ›› Issue (2): 99-101.
董人菘,王华,张晓钟,余正涛,张涛
DONG Ren-song,WANG Hua,ZHANG Xiao-zhong,YU Zheng-tao and ZHANG Tao
摘要: 为提高汉-英统计机器翻译的翻译效果,提出一个基于依存句法关系的语言模型,在较成熟的基于短语翻译的统计特征下,对解码产生的NBEST候选翻译结果进行进一步约束,重新计算得分,调整NBEST候选翻译序列,以得到最佳翻译。实验以“Pharaoh”为比较基准,以500句汉英句对为测试集,最终的实验结果表明,提出的基于依存句法关系的语言模型可以在一定程度上提高汉-英统计机器翻译最佳翻译的正确率。
[1] Wu De-kai.Stochastic inversion transduction grammars and bilingual parsing of parallel corpora[J].Computational Linguistics,1997,23(3):377-403 [2] Chiang D.A hierarchical phrase-based model for statistical machine translation[C]∥Proceedings of ACL.2005:263-270 [3] Yamada K,Knight K.A syntax-based statistical translationmodel[C]∥Proceedings of ACL.Toulose,France,2001:523-530 [4] Galley M,Hopkins M,Knight K,et al.What’s in a translation rule?[C]∥Proceedings of the 2004Human Language Techno-logy Conference of the North American Chapter of the Association for Computational Linguistics.Boston,Massachusetts,2004:273-280 [5] Lin D,Cherry C.Word alignment with cohesion constraint[C]∥Proceedings of the HLT-NAACL.Edmonton,Canada,2003:49-51 [6] Quirk C,Menezes A,Cherry C.Dependency treelet translation:Syntactically informed phrasal SMT[C]∥Proceedings of ACL.Ann Arbor,Michigan,2005:271-279 [7] 熊德意.基于括号转录语法和依存语法的统计机器翻译研究[D].北京:中国科学院计算技术研究所,2007 |
No related articles found! |
|