Improving English-Vietnamese Word Alignment Using Translation Model

Author

Nguyen, Giang Thanh ; Dinh, Dien

Author_Institution

Linguistic R&D Dept., Kim Tu Dien Multilingual Data Center, Ho Chi Minh City, Vietnam

fYear

2012

fDate

Feb. 27 2012-March 1 2012

Firstpage

1

Lastpage

4

Abstract

Word alignment for a parallel corpus is the connection between the words/phrases in source language and the words/phrases in target language. The alignment result is an important input for many natural language processing applications. In this paper, we propose an approach to improve the English-Vietnamese word alignment result by using the alignment frequency that is presented in the translation model of SMT (Statistical Machine Translation). We also indicate 5 common error types of English-Vietnamese word alignment and propose the heuristic patterns to discover the alignment errors. The experimental results show the improvement compared to the result of GIZA++.

Keywords

language translation; natural language processing; statistical analysis; English-Vietnamese word alignment; alignment errors; alignment frequency; heuristic patterns; natural language processing; statistical machine translation; translation model; Computational linguistics; Computational modeling; Feature extraction; Heuristic algorithms; Hidden Markov models; Measurement; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), 2012 IEEE RIVF International Conference on

Conference_Location

Ho Chi Minh City

Print_ISBN

978-1-4673-0307-1

Type

conf

DOI

10.1109/rivf.2012.6169841

Filename

6169841