Bagging and Boosting statistical machine translation systems

	Bagging and Boosting statistical machine translation systems
	Xiao, Tong 1; Zhu, Jingbo 1; Liu, Tongran2 ; Liu, TR (reprint author), Chinese Acad Sci, Inst Psychol, Key Lab Behav Sci, 10A Datun Rd, Beijing 100101, Peoples R China.
心理所单位排序	2
摘要	In this article we address the issue of generating diversified translation systems from a single Statistical Machine Translation (SMT) engine for system combination. Unlike traditional approaches, we do not resort to multiple structurally different SMT systems, but instead directly learn a strong SMT system from a single translation engine in a principled way. Our approach is based on Bagging and Boosting which are two instances of the general framework of ensemble learning. The basic idea is that we first generate an ensemble of weak translation systems using a base learning algorithm, and then learn a strong translation system from the ensemble. One of the advantages of our approach is that it can work with any of current SMT systems and make them stronger almost "for free". Beyond this, most system combination methods are directly applicable to the proposed framework for generating the final translation system from the ensemble of weak systems. We evaluate our approach on Chinese-English translation in three state-of-the-art SMT systems, including a phrase-based system, a hierarchical phrase-based system and a syntax-based system. Experimental results on the NIST MT evaluation corpora show that our approach leads to significant improvements in translation accuracy over the baselines. More interestingly, it is observed that our approach is able to improve the existing system combination systems. The biggest improvements are obtained by generating weak systems using Bagging/Boosting, and learning the strong system using a state-of-the-art system combination method. (C) 2012 Elsevier B.V. All rights reserved.
关键词	Statistical machine translation Ensemble learning System combination
学科领域	Other Applied Psychology
	2013
语种	英语
发表期刊	ARTIFICIAL INTELLIGENCE
ISSN	0197-4556
卷号	195 页码:496-527
期刊论文类型	期刊论文
URL	查看原文
收录类别	SCI
项目简介	This work was supported in part by the National Science Foundation of China (Grant Nos.: 61073140, 61272376), the Natural Science Foundation for the Youth of China (Grant No.: 31000468), Specialized Research Fund for the Doctoral Program of Higher Education (Grant No.: 20100042110031) and the Fundamental Research Funds for the Central Universities. The authors would like to thank the anonymous reviewers of ACL 2010 and the AI journal for their pertinent comments, Chunliang Zhang and Shujie Yao for their valuable suggestions for improving this article, and Tianning Li and Rushan Chen for developing parts of the baseline systems.
WOS关键词	RECOGNITION ; COMBINATION ; ALGORITHMS ; LANGUAGE
WOS标题词	Science & Technology ; Technology
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000315839600019
资助机构	National Science Foundation of China [61073140, 61272376] ; Natural Science Foundation for the Youth of China [31000468] ; Specialized Research Fund for the Doctoral Program of Higher Education [20100042110031] ; Fundamental Research Funds for the Central Universities
引用统计	被引频次：19[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.psych.ac.cn/handle/311026/10737
专题	中国科学院行为科学重点实验室
通讯作者	Liu, TR (reprint author), Chinese Acad Sci, Inst Psychol, Key Lab Behav Sci, 10A Datun Rd, Beijing 100101, Peoples R China.
作者单位	1.Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China 2.Chinese Acad Sci, Inst Psychol, Key Lab Behav Sci, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Xiao, Tong,Zhu, Jingbo,Liu, Tongran,et al. Bagging and Boosting statistical machine translation systems[J]. ARTIFICIAL INTELLIGENCE,2013,195:496-527.
APA	Xiao, Tong,Zhu, Jingbo,Liu, Tongran,&Liu, TR .(2013).Bagging and Boosting statistical machine translation systems.ARTIFICIAL INTELLIGENCE,195,496-527.
MLA	Xiao, Tong,et al."Bagging and Boosting statistical machine translation systems".ARTIFICIAL INTELLIGENCE 195(2013):496-527.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
WOS000315839600019.p（1214KB）			限制开放	CC BY-NC-SA	请求全文