A Relationship: Word Alignment, Phrase Table, and Translation Quality

In the last years, researchers conducted several studies to evaluate the machine translation quality based on the relationship between word alignments and phrase table. However, existing methods usually employ ad-hoc heuristics without theoretical support. So far, there is no discussion from the asp...

Full description

Saved in:
Bibliographic Details
Main Authors: Liang Tian, Derek F. Wong, Lidia S. Chao, Francisco Oliveira
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1155/2014/438106
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850171801758334976
author Liang Tian
Derek F. Wong
Lidia S. Chao
Francisco Oliveira
author_facet Liang Tian
Derek F. Wong
Lidia S. Chao
Francisco Oliveira
author_sort Liang Tian
collection DOAJ
description In the last years, researchers conducted several studies to evaluate the machine translation quality based on the relationship between word alignments and phrase table. However, existing methods usually employ ad-hoc heuristics without theoretical support. So far, there is no discussion from the aspect of providing a formula to describe the relationship among word alignments, phrase table, and machine translation performance. In this paper, on one hand, we focus on formulating such a relationship for estimating the size of extracted phrase pairs given one or more word alignment points. On the other hand, a corpus-motivated pruning technique is proposed to prune the default large phrase table. Experiment proves that the deduced formula is feasible, which not only can be used to predict the size of the phrase table, but also can be a valuable reference for investigating the relationship between the translation performance and phrase tables based on different links of word alignment. The corpus-motivated pruning results show that nearly 98% of phrases can be reduced without any significant loss in translation quality.
format Article
id doaj-art-ab973ba83ddb49b5b0c8a31f5c888f95
institution OA Journals
issn 2356-6140
1537-744X
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series The Scientific World Journal
spelling doaj-art-ab973ba83ddb49b5b0c8a31f5c888f952025-08-20T02:20:12ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/438106438106A Relationship: Word Alignment, Phrase Table, and Translation QualityLiang Tian0Derek F. Wong1Lidia S. Chao2Francisco Oliveira3Natural Language Processing & Portuguese-Chinese Machine Translation Laboratory, Department of Computer and Information Science, University of Macau, MacauNatural Language Processing & Portuguese-Chinese Machine Translation Laboratory, Department of Computer and Information Science, University of Macau, MacauNatural Language Processing & Portuguese-Chinese Machine Translation Laboratory, Department of Computer and Information Science, University of Macau, MacauNatural Language Processing & Portuguese-Chinese Machine Translation Laboratory, Department of Computer and Information Science, University of Macau, MacauIn the last years, researchers conducted several studies to evaluate the machine translation quality based on the relationship between word alignments and phrase table. However, existing methods usually employ ad-hoc heuristics without theoretical support. So far, there is no discussion from the aspect of providing a formula to describe the relationship among word alignments, phrase table, and machine translation performance. In this paper, on one hand, we focus on formulating such a relationship for estimating the size of extracted phrase pairs given one or more word alignment points. On the other hand, a corpus-motivated pruning technique is proposed to prune the default large phrase table. Experiment proves that the deduced formula is feasible, which not only can be used to predict the size of the phrase table, but also can be a valuable reference for investigating the relationship between the translation performance and phrase tables based on different links of word alignment. The corpus-motivated pruning results show that nearly 98% of phrases can be reduced without any significant loss in translation quality.http://dx.doi.org/10.1155/2014/438106
spellingShingle Liang Tian
Derek F. Wong
Lidia S. Chao
Francisco Oliveira
A Relationship: Word Alignment, Phrase Table, and Translation Quality
The Scientific World Journal
title A Relationship: Word Alignment, Phrase Table, and Translation Quality
title_full A Relationship: Word Alignment, Phrase Table, and Translation Quality
title_fullStr A Relationship: Word Alignment, Phrase Table, and Translation Quality
title_full_unstemmed A Relationship: Word Alignment, Phrase Table, and Translation Quality
title_short A Relationship: Word Alignment, Phrase Table, and Translation Quality
title_sort relationship word alignment phrase table and translation quality
url http://dx.doi.org/10.1155/2014/438106
work_keys_str_mv AT liangtian arelationshipwordalignmentphrasetableandtranslationquality
AT derekfwong arelationshipwordalignmentphrasetableandtranslationquality
AT lidiaschao arelationshipwordalignmentphrasetableandtranslationquality
AT franciscooliveira arelationshipwordalignmentphrasetableandtranslationquality
AT liangtian relationshipwordalignmentphrasetableandtranslationquality
AT derekfwong relationshipwordalignmentphrasetableandtranslationquality
AT lidiaschao relationshipwordalignmentphrasetableandtranslationquality
AT franciscooliveira relationshipwordalignmentphrasetableandtranslationquality