Syntactic Pattern Based Word Alignment for Statistical Machine Translation

Quang-Hung Le and Anh-Cuong Le
Additional contact information
Quang-Hung Le: Faculty of Information Technology, Quynhon University, Vietnam & University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam
Anh-Cuong Le: University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam

International Journal of Knowledge and Systems Science (IJKSS), 2014, vol. 5, issue 3, 36-45

Abstract: Word alignment is the task of aligning bilingual words in a corpus of parallel sentences, and determining the probabilities for these aligned bilingual word pairs. It is the most important factor affecting the quality of any Statistical Machine Translation (SMT) systems. The IBM word alignment models are most well-known in the SMT research community. These models are pure statistical models and therefore they are not good for some language pairs which have differences in linguistic aspects (e.g. grammatical structures). This paper aims to improve the IBM models by using syntactic information. The authors first propose a new type of constraint based on bilingual syntactic patterns, and then integrate it into the IBM models. Finally, they show how to estimate the models' parameters using this new type of constraint. The experiments are conducted on the English-Vietnamese language pair for evaluation.

Date: 2014
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/ijkss.2014070103 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jkss00:v:5:y:2014:i:3:p:36-45

Access Statistics for this article

International Journal of Knowledge and Systems Science (IJKSS) is currently edited by Van Nam Huynh

More articles in International Journal of Knowledge and Systems Science (IJKSS) from IGI Global
Bibliographic data for series maintained by Journal Editor ().