引入集成学习的最大熵短语调序模型

摘要
参考文献
相关文章 (15)

全文: PDF (828 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要基于最大熵的括号转录语法模型具有翻译能力强、模型训练简单的优点,成为近些年统计机器翻译研究的热点。然而,该模型存在短语调序实例样本分布不平衡的缺点。针对该问题,该文提出了一种引入集成学习的短语调序模型训练方法。在大规模数据集上的实验结果表明,我们的方法能有效改善调序模型的训练效果,显著提高翻译系统性能。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	何钟豪
	苏劲松
	史晓东
	陈毅东
	黄研洲

关键词 ：最大熵, 短语调序, 不平衡分类, 集成学习

Abstract：The Maximum Entropy Based BTG model becomes a hot topic in statistical machine translation in recent years due to its strong translation and easy-to-train abilities. However, the distribution of reordering examples in this model is imbalanced. To solve this problem, we introduce an ensemble learning method for training phrase reordering model. Experimental results show that,the reordering model can reach a better training effect via our method and the performance of the translation system is improved significantly in a large-scale dataset.

Key words： maximum entropy phrase reordering imbalanced classifier ensemble learning

收稿日期: 2013-03-22

中图分类号:

TP391

基金资助:国家自然科学基金(61303082,61005052);国家科技支撑计划(2012BAH14F03);高等学校博士学科点专项科研基金(20120121120046)

作者简介: 何钟豪(1990-),硕士研究生,主要研究领域为自然语言处理与机器翻译。苏劲松(1982-),博士,助理教授,主要研究领域为自然语言处理与机器翻译。史晓东(1966-),博士,教授,主要研究领域为自然语言处理与机器翻译。

链接本文:

http://jcip.cipsc.org.cn/CN/Y2014/V28/I1/87

[1] 熊德意.基于括号转录语法和依存语法的统计机器翻译研究[D].北京: 中国科学院计算技术研究所,2007.
[2] Dekai Wu. Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora[J]. Computational linguistics,1997,25(6): 377-403.
[3] 刘群. 基于句法的统计机器翻译模型与方法. 中文信息学报. 2011, 25(6): 63-71.
[4] Deyi Xiong,Qun Liu, Shouxun Lin. Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation[C]//Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics,Sydney, Australia,2006: 521-528.
[5] Deyi Xiong,Min Zhang,Aiti Aw. A linguistically annotated reordering model for BTG-based statistical machine translation[C]//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies,Columbus,Ohio,USA,2008: 149-152
[6] Min Zhang,Haizhou Li. Tree kernel-based SVM with structured syntactic knowledge for BTG-based phrase reordering[C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing,Suntec,Singapore,2009: 698-707.
[7] Jinsong Su,Yang Liu,Haitao Mi. Dependency-based bracketing transduction grammar for statistical machine translation[C]//Proceedings of the 23rd International Conference on Computational Linguistics,Beijing,China,2010: 1185-1193.
[8] Hanbin Chen,Jiancheng Wu, Jason S Chang. Learning bilingual linguistic reordering model for statistical machine translation[C]//Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics,Boulder Colorado,USA,2009: 254-262.
[9] 孙萌,姚建民,吕雅娟,等. 基于最大熵短语调序模型的特征抽取算法改进[J]. 中文信息学报,2011,25(2): 78-82.
[10] Shoushan Li,Guodong Zhou,Zhongqing Wang. Imbalanced Sentiment Classification[C]//Proceedings of the 20th ACM international conference on information and knowledge management,Glasgow,Scotland,UK,2011: 2469-2472.
[11] 叶志飞,文益民,吕宝粮. 不平衡分类问题研究综述[J]. 智能系统学报,2009,4(2): 148-156.
[12] Zhongqing Wang,Shoushan Li,Guodong Zhou. Imbalanced Sentiment Classification with Multi-Strategy Ensemble Learning[C]//Proceedings of the International Conference on Asian Language Processing,Penang,Malaysia,2011: 131-134.
[13] 钱洪波,贺广南. 非平衡类数据分类概述[J]. 计算机工程与科学,2010,32(5): 85-88.
[14] Leo Breiman. Bagging Predictors[J], Machine Learning,1996a,24: 123-140.
[15] Franz Josef Och. Minimum Error Rate Training in Statistical Machine Translation[C]//Proceedings of the 41rd Annual Meeting of the Association for Computational Linguistics,Sapporo,Japan,2003: 160-167.
[16] 张仰森,郭江. 动态自适应加权的多分类器融合词义消歧模型[J]. 中文信息学报,2012,26(1): 3-8.
[17] Franz Josef Och,Hermann Ney. Discriminative training and maximum entropy models for statistical machine translation[C]//Proceedings of the 40th Annual Meeting of the Association forComputational Linguistics,Philadelphia,2002: 295-302.
[18] Franz Josef Och,Hermann Ney.Improved statisticalalignment models[C]//Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics,Hong Kong,2000: 440-447.
[19] Kishore Papineni,SalimRoukos,Todd Ward. BLEU: a Method for Automatic Evaluation of Machine Translation[C]//Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics,Philadelphia,2002: 311-318.
[20] Ying Zhang,Stephan Vogel,Alex Waibel. Interpreting BLEU/NIST Scores: How Much Improvement Do We Need to Havea Better System?[C]//Proceedings of The International Conference on Language Resources and Evaluation,Lisbon,Portugal,2004: 2051-2054.