数字图书馆多语言信息存取和元数据记录的机器翻译被引量：3

Multilingual Information Access for Digital Libraries and the Machine Translation of Metadata Records

导出

摘要多语言信息存取(MLIA:Multilingual Information Access)是许多数字图书馆希望提供的一种服务。本文从MLIA的概念入手,探讨了机器翻译(MT)在实现数字图书馆的多语言信息存取服务中的作用。为了评测目前MT系统的性能以确定它们能否应用于数字图书馆的多语言信息存取,我们开发了一个多语种的元数据机器翻译综合评价平台HeMT(Human Evaluation of Machine Translation.http://txcdk-v10.unt.edu/HeMT/)。利用HEMT平台6大功能模块,评价了3个在线机器翻译系统所译的2000条元数据记录。这些记录来自北德克萨斯大学(UNT)图书馆和德克萨斯州历史门户(The Portal to Texas History),在报告评价结果的基础上,对所发现的机器翻译的错误进行了分析,文章最后提出了使用多引擎机器翻译(Multi-engine Machine Translation)技术以提高元数据记录翻译性能的设想。 This paper describes the role of machine translation (MT) for multilingual information access, a service that is desired by digital libraries that wish to provide cross-cultural accessto their collections. To understand the performance of current MT systems, we have developed an integrated multilingual evaluation platform HeMT(http://txcdk-v10.unt.edu/HeMT/). HeMT consists six functional modules to facilitate human evaluation of machine translation. We have performed evaluation of three online MT services on 2000 metadata records that were extracted from two digital collections. This paper will report the evaluations on Chinese translation. Additionally, we present the analysis of the translation errors and propose Multi-engine MT strategies to improve translation performance.

作者陈江萍

机构地区北德克萨斯大学信息学院

出处《公共图书馆》 2012年第3期51-58,共8页 Public Library Journal

基金美国博物馆及图书馆服务机构(IMLS)的资助资助号LG-06-10-0162-10

关键词数字图书馆元数据机器翻译多语言信息存取 Digital library Metadata record Machine translation HEMT MLIA

分类号 G250.76 [文化科学—图书馆学] H085 [语言文字—语言学]

引文网络
相关文献

参考文献10

1Antti-Veikko I Rosti,Necip Fazil Ayan,Bing Xiang,Spyros Matsoukas,Richard Schwartz,Bonnie J.Dorrt.Combing Outputs from Multiple Machine Translation Systems[].HLT-NAACL.2007
2Matusov E,Ueffing N.Computing Consensus Translation from Multiple Machine Translation Systems Using Enhanced Hypotheses Alignment[].Procof Conference of Association for Computational Linguistics.2006
3Yasuhiro Akiba,,Taro Watanabe,and Eiichiro Sumita.Using language and translation models to select the best among outputs from multiple MT systems. Proc. COLING-2002 . 2002
4Chris Callison-Burch,Cameron Fordyce,Philipp Koehn,Christof Monz,Josh Schroeder.(Meta-) Evaluation of Machine Translation[].Proceedings of ACL- Workshop on Statistical Machine Translation.2007
5CaLLISON-BURCH C,KOEHN P,MONZ C, et al.Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Transla- tion[].Proceedings of the Joint Fifth Workshop on Statistical Machine Transla- tion and MetricsMATRWMT’’.2010
6Nomoto,Tadashi.Multi-engine machine translation with voted language model[].Proceedings of ACL.2004
7Oard,D.Cross-language information retrieval[].Annual review of Information Science and Technology.1999
8Oard D W,He D Q,Wang J Q.User assisted query translation for interactive cross-language information retrieval[].Information Pro-cessing and Management.2008
9Tidhar,Dan,Uwe Küssner.Learning to Select a Good Translation[].Proceedings of the ~(th) International Conference on Computational Linguistics (COLING).2000
10Yates S.Scaling the tower of babel fish:An analysis of the ma-chine translation of legal information[].Law Library Journal.2006