UM  > 科技學院
Phrase Oriented Word Alignment Method
Liang Tian; Fai Wong; Sam Chao
2011
Conference Namethe 7th China Workshop on Machine Translation
Source PublicationProceedings of the 7th China Workshop on Machine Translation
Pages237–250
Conference Date2011
Conference PlaceXiamen, China.
Abstract

Automatic word alignment plays a very important role in statistical machine translation research area. However, the alignment result generated by GIZA++ is not satisfied. In this paper, an alignment method based on Maximum Matching Method (MMM) and GIZA++ is proposed. Firstly, the words and phrases of parallel English and Chinese sentences are detected based on Maximum Matching Method (MMM), and then candidate alignment results are gotten by the constraint of both a dictionary and GIZA++ result. Empirical study demonstrates that the proposed method gives a better alignment result than that of the GIZA++, especially for parallel sentences that have phrases.

KeywordAutomatic Word Alignment, Giza++++ Dictionary Maximum Matching Method Statistical Machine Translation
Language英语
Fulltext Access
Document TypeConference paper
CollectionFaculty of Science and Technology
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
AffiliationPortuguese-Chinese Machine Translation Lab, University of Macau, Macau
Recommended Citation
GB/T 7714
Liang Tian,Fai Wong,Sam Chao. Phrase Oriented Word Alignment Method[C],2011:237–250.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liang Tian]'s Articles
[Fai Wong]'s Articles
[Sam Chao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liang Tian]'s Articles
[Fai Wong]'s Articles
[Sam Chao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liang Tian]'s Articles
[Fai Wong]'s Articles
[Sam Chao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.