期刊文献+

Naxi-English Bilingual Word Alignment Based on Language Characteristics and Log-Linear Model

Naxi-English Bilingual Word Alignment Based on Language Characteristics and Log-Linear Model
下载PDF
导出
摘要 We propose a method that can achieve the Naxi-English bilingual word automatic alignment based on a log-linear model.This method defines the different Naxi-English structural feature functions,which are English-Naxi interval switching function and Naxi-English bilingual word position transformation function.With the manually labeled Naxi-English words alignment corpus,the parameters of the model are trained by using the minimum error,thus Naxi-English bilingual word alignment is achieved automatically.Experiments are conducted with IBM Model 3 as a benchmark,and the Naxi language constraints are introduced.The final experiment results show that the proposed alignment method achieves very good results:the introduction of the language characteristic function can effectively improve the accuracy of the Naxi-English Bilingual Word Alignment. We propose a method that can achieve the Naxi-English bilingual word automatic align- ment based on a log-linear model. This method defines the different Naxi-English structural fea- ture functions, which are English-Naxi interval switching function and Naxi-English bilingual word position transformation function. With the manually labeled Naxi-English words alignment corpus, the parameters of the model are trained by using the minimum error, thus Naxi-English bilingual word alignment is achieved automatical- ly. Experiments are conducted with IBM Model 3 as a benchmark, and the Naxi language con- straints are introduced. The final experiment re- sults show that the proposed alignment method a- chieves very good results: the introduction of the language characteristic function can effectively improve the accuracy of the Naxi-English Bilin- gual Word Alignment.
出处 《China Communications》 SCIE CSCD 2012年第3期78-86,共9页 中国通信(英文版)
基金 supported by the National Nature Science Foundation of China under Grants No.60863011,No.61175068,No.61100205,No.60873001 the Fundamental Research Funds for the Central Universities under Grant No.2009RC0212 the National Innovation Fund for Technology-based Firms under Grant No.11C26215305905 the Open Fund of Software Engineering Key Laboratory of Yunnan Province under Grant No.2011SE14
关键词 对数线性模型 词对齐 双语 语言 纳西族 自动对齐 结构特征 转换功能 word aligrmaent Naxi language English log-linear model interval switching function posi-tion transformation function
  • 相关文献

参考文献18

  • 1杨沐昀,Li,Sheng,Zhao,Tiejun,Lu,Yajuan,Liu,Zhanyi.A Research on Bilingual Dictionary Based Sentence Alignment for Chinese English Parallel Corpus[J].High Technology Letters,2002,8(1):8-11. 被引量:3
  • 2SADAT F. Using Comparable Corpora to Improve the Effectiveness of Cross-language Information Retrieval[C]// Proceedings of the 7th International Conference on Advances in Natural Language Processing: August, 2010, Reykjavik, Iceland: 320-331.
  • 3CICEKLI I, GUVENIR H A. Learning Translation Templates from Bilingual Translation Examples[J]. Applied Intelligence, 2001, 15(1): 57-76.
  • 4LIN Yongzhao, LIU Xuewen. Two Classes of Modulation Schemes for Deep Space Communications[J]. China Co- mmutations, 2006, 4(6): 95-103.
  • 5BROWN P F, PIETRA D S A, PIETRA D V J, et al. TheMathematics of Statistical Machine Translation: Parameter estimation[J]. Computational Linguistics, 1993, 19(2): 263-311.
  • 6OCH F J, NEY I:L Discriminative Training and Maximum Entropy Models for Statistical machine Translation[C]// Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics: July 2002, Philadelphia: 295 -302.
  • 7LIU Yang, LIU Qun, LIN Shouxun. Log-linear Models for Word Alignment[C]// Proceedings of the 43th Annual Meeting of the Association for Computational Linguistics : 2005, Ann Arbor, USA: 459-466.
  • 8SMAEL G V, OCH F J, NEY H, et al. mproving Alignment Quality in Statistical Machine Translation Using Context-dependent Maximum Entropy Models[C]// Pro- ceedings of the 19th International Conferenceon computational Linguitic s: 2002, Taipei: 1-7.
  • 9OCH F J, NEY H. A Systematic Comparison of Various Statistical Alignment Models[J]. Computational Linguistics, 2003, 29(1): 19-51.
  • 10LIU Yang. Research on Tree to String Statically Translation Model[D]. Beijing: Institute of Computing Technology, Chinese Academy of Sciences, 2007.

二级参考文献7

  • 1Elliott Macklovitch,Marie-Louise Hannan.Line ‘Em Up: Advances in Alignment Technology and their Impact on Translation Support Tools[J].Machine Translation.1998(1)
  • 2Brown P F,Cocke J,Pietra S A,et al. Computational Linguistics . 1990
  • 3Wang B.Automatic alignment on Chinese-English bilingual corpora[]..1999
  • 4Kay M,Rocheisen M. Computational Linguistics . 1993
  • 5Liu X,Zhou M,et al. Computer Journal . 1998
  • 6Dagan I,Itai A.Word sense disambiguation using a second language monolingual corpus[].Computational Linguistics.1994
  • 7Liu X.Research on methods of word sense disambiguation in English-Chinese machine translation: [ dissertation ][]..1998

共引文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部