Improving Word Alignment Through Morphological Analysis

被引：0

作者：

Vuong Van Bui ^{[1
]}

Thanh Trung Tran ^{[1
]}

Nhat Bich Thi Nguyen ^{[1
]}

Tai Dinh Pham ^{[1
]}

Anh Ngoc Le ^{[1
]}

Cuong Anh Le ^{[1
]}

机构：

[1] Univ Engn & Technol, Vietnam Natl Univ, Dept Comp Sci, Hanoi, Vietnam

来源：

INTEGRATED UNCERTAINTY IN KNOWLEDGE MODELLING AND DECISION MAKING, IUKM 2015 | 2015年 / 9376卷

关键词：

Machine translation; Word alignment; IBM models; Morphological analysis;

D O I：

10.1007/978-3-319-25135-6_30

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Word alignment plays a critical role in statistical machine translation systems. The famous word alignment system, IBM models series, currently operates on only surface forms of words regardless of their linguistic features. This deficiency usually leads to many data sparseness problems. Therefore, we present an extension that enables the integration of morphological analysis into the traditional IBM models. Experiments on English-Vietnamese tasks show that the new model produces better results not only in word alignment but also in final translation performance.

引用

页码：315 / 325

页数：11

共 11 条

[1]

[Anonymous], EMNLP CONLL

[2]

[Anonymous], P 40 ANN M ASS COMP

[3]

[Anonymous], P 41 ANN M ASS COMP

[4]

Brown P. F., 1993, Computational Linguistics, V19, P263

[5]

Brown PeterF., 1993, HUMAN LANGUAGE TECHN, P202

[6]

Federico M, 2008, INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, P1618

[7]

Koehn P., 2007, MOSES OPEN SOURCE TO

[8]

Lee S.Y., 2004, the Proceedings of the Human Language Technology, Conference of the North American Chapter of the Association For Computational Linguistics, P57

[9]

Moore R.C., 2004, Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL 2004), P518

[10]

Och FJ, 2003, COMPUT LINGUIST, V29, pc, DOI 10.1162/089120103321337421

← 1 2 →