基于释义信息的维汉机器翻译系统融合研究

doi:10.19678/j.issn.1000-3428.0050313

计算机工程 ›› 2019, Vol. 45 ›› Issue (4): 288-295,301. doi: 10.19678/j.issn.1000-3428.0050313

基于释义信息的维汉机器翻译系统融合研究

王亚娟^1,2,3,4,李晓^1,3,杨雅婷^1,3,米成刚^1,3

1.中国科学院新疆理化技术研究所,乌鲁木齐 830011; 2.中国科学院大学,北京 100049; 3.新疆民族语音语言信息处理实验室,乌鲁木齐 830011; 4.新疆警察学院信息安全工程系,乌鲁木齐 830011

收稿日期:2018-01-29 出版日期:2019-04-15 发布日期:2019-04-15
作者简介:王亚娟(1983—),女,讲师、博士研究生,主研方向为多语种信息处理;李晓,研究员、博士生导师;杨雅婷,副研究员、博士;米成刚,助理研究员、博士。
基金资助:
国家自然科学基金（U1703133）；中科院西部之光人才培养引进计划（2017-XBQNXZ-A-005）；中国科学院青年创新促进会项目（2017472）；新疆维吾尔自治区重大科技专项（2016A03007-3）；新疆维吾尔自治区高层次人才引进工程（Y839031201）。

Research of Uyghur-Chinese Machine Translation System Combination Based on Paraphrase Information

WANG Yajuan^1,2,3,4,LI Xiao^1,3,YANG Yating^1,3,MI Chenggang^1,3

1.Xinjiang Technical Institute of Physics and Chemistry,Chinese Academy of Sciences,Urumqi 830011,China; 2.University of Chinese Academy of Sciences,Beijing 100049,China; 3.Xinjiang Laboratory of Minority Speech and Language Information Processing,Urumqi 830011,China; 4.Department of Information Security Engineering,Xinjiang Police College,Urumqi 830011,China

Received:2018-01-29 Online:2019-04-15 Published:2019-04-15

摘要/Abstract

摘要：

针对维汉机器翻译中单个翻译模型翻译效果差且多个翻译模型间翻译差异较大的问题,提出一种基于释义信息的系统融合方法。通过提取汉语端释义信息对汉语翻译假设进行词对齐，利用词对齐信息构建并解码混淆网络，从而得到维汉机器翻译系统融合结果。实验结果表明,与单个翻译系统HPSTW相比,该方法能够有效提高翻译质量。

关键词: 维汉机器翻译, 释义信息, 系统融合, 翻译假设词对齐, 释义表过滤

Abstract:

Aiming at the problem that the translation effect of single translation model in Uyghur-Chinese machine translation is poor and the translation difference between multiple translation models is large,a system fusion method based on paraphrase information is proposed.By extracting the Chinese interpretation information,the Chinese translation hypothesis is word aligned,and the word alignment information is used to construct and decode the confusion network,and the fusion result of the Uyghur-Chinese machine translation system is obtained.Experimental results show that compared with the single translation system HPSTW,this method can effectively improve the translation quality.

Key words: Uyghur-Chinese machine translation, paraphrase information, system combination, translation hypothesis word alignment, paraphrase table filtration

中图分类号:

TP391

王亚娟,李晓,杨雅婷,米成刚. 基于释义信息的维汉机器翻译系统融合研究[J]. 计算机工程, 2019, 45(4): 288-295,301.

WANG Yajuan,LI Xiao,YANG Yating,MI Chenggang. Research of Uyghur-Chinese Machine Translation System Combination Based on Paraphrase Information[J]. Computer Engineering, 2019, 45(4): 288-295,301.

http://www.ecice06.com/CN/Y2019/V45/I4/288

参考文献

［1］李晓,蒋同海,周喜,等.维汉机器翻译关键技术研究概述［J］.网络新媒体技术,2016,5(1):19-25.
［2］KOEHN P,OCH F J,MARCU D.Statistical phrase-based translation［C］//Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology.Stroudsburg,USA:Association for Computational Linguistics,2003:48-54.
［3］CHIANG D.Hierarchical phrase-based translation ［J］.Computational Linguistics,2007,33(2):201-228.
［4］DURRANI N,FRASER A,SCHMID H,et al.Can Markov models over minimal translation units help phrase-based SMT? ［C］//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics.Stroudsburg,USA:Association for Computational Linguistics,2013:399-405.
［5］李晓,蒋同海,周喜,等.面向复杂形态语言机器翻译的多模型融合词性标注研究［J］.网络新媒体技术,2014,3(1):60-64.
［6］PETER J T,ALKHOULI T,NEY H,et al.The QT21/HimL combined machine translation system ［C］//Proceedings of the 1st Conference on Machine Translation.Stroudsburg,USA:Association for Computational Linguistics,2016:344-355.
［7］DURRANI N,DALVI F,SAJJAD H,et al.QCRI machine translation systems for IWSLT 16 ［EB/OL］.［2017-12-20］.https://arxiv.org/pdf/1701.03924.pdf.
［8］BANGALORE B,BORDEL G,RICCARDI G.Computing consensus translation from multiple machine translation systems［C］//Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding.Washington D.C.,USA:IEEE Press,2001:351-354.
［9］FREITAG M,PETER J T,PEITZ S,et al.Local system voting feature for machine translation system combination［C］//Proceedings of the 10th Workshop on Statistical Machine Translation.Stroudsburg,USA:Association for Computational Linguistics,2015:467-476.
［10］ROSTI A V I,HE X,KARAKOS D,et al.Review of hypothesis alignment algorithms for MT system combination via confusion network decoding［C］//Proceedings of the 7th Workshop on Statistical Machine Translation.Stroudsburg,USA:Association for Computational Linguistics,2012:191-199.
［11］GONZLEZ-RUBIO J,CASACUBERTA F.Minimum Bayes’ risk subsequence combination for machine translation［J］.Pattern Analysis and Applications,2015,18(3):523-533.
［12］ZHANG H,WANG D H,LIU C L.Character confidence based on N-best list for keyword spotting in online Chinese handwritten documents［J］.Pattern Recognition,2014,47(5):1880-1890.
［13］KARAKOS D,EISNER J,KHUDANPUR S,et al.Machine translation system combination using ITG-based alignments［C］//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies.Stroudsburg,USA:Association for Computational Linguistics,2008:81-84.
［14］FREITAG M,HUCK M,NEY H.Jane:open source machine translation system combination［C］//Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics.Stroudsburg,USA:Association for Computational Linguistics,2014:29-32.
［15］HEAFIELD K,LAVIE A.Combining machine translation output with open source:the carnegie mellon multi-engine machine translation scheme［J］.The Prague Bulletin of Mathematical Linguistics,2010,93(1):27-36.
［16］张丽林,李茂西,肖文艳,等.机器翻译自动评价中领域知识复述抽取研究［J］.北京大学学报(自然科学版),2017,53(2):230-238.
［17］AL-SMADI M,JARADAT Z,AL-AYYOUB M,et al.Paraphrase identification and semantic text similarity analysis in Arabic news tweets using lexical,syntactic,and semantic features［J］.Information Processing and Management,2017,53(3):640-652.
［18］SERAJ R M,SIAHBANI M,SARKAR A.Improving statistical machine translation with a multilingual paraphrase database［C］//Proceedings of Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:Association for Computational Linguistics,2015:1379-1390.
［19］MA W Y,MCKEOWN K.System combination for machine translation through paraphrasing［C］//Proceedings of Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:Association for Computational Linguistics,2015:1053-1058.
［20］GHANNAY S,BARRAULT L.Using hypothesis selection based features for confusion network MT system combination［C］//Proceedings of the 3rd Workshop on Hybrid Approaches to Translation.Stroudsburg,USA:Association for Computational Linguistics,2014:1-5.
［21］RIKTERS M,SKADINA I.Combining machine translated sentence chunks from multiple MT systems［C］//Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics.Berlin,Germany:Springer,2016:27-37.
［22］YIMAM S M,ALONSO H M,RIEDL M,et al.Learning paraphrasing for multiword expressions［C］//Proceedings of the 12th Workshop on Multiword Express-ions.Stroudsburg,USA:Association for Computational Linguistics,2016:1-10.
［23］PAVLICK E,RASTOGI P,GANITKEVITCH J,et al.PPDB2.0:better paraphrase ranking,fine-grained entailment relations,word embeddings,and style classification［C］//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Stroudsburg,USA:Association for Computational Linguistics,2015:425-430.
［24］DENKOWSKI M,LAVIE A.Meteor universal:language specific translation evaluation for any target language［C］//Proceedings of the 9th Workshop on Statistical Machine Translation.Stroudsburg,USA:Association for Computational Linguistics,2014:376-380.
［25］KOEHN P,HOANG H,BIRCH A,et al.Moses:open source toolkit for statistical machine translation［C］//Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions.Stroudsburg,USA:Association for Computational Linguistics,2007:177-180.
［26］TURSUN E,GANGULY D,OSMAN T,et al.A semisupervised tag-transition-based markovian model for uyghur morphology analysis［J］.ACM Transactions on Asian and Low-Resource Language Information Processing,2016,16(2).
［27］STOLCKE A.SRILM——an extensible language modeling toolkit［C］//Proceedings of International Conference on Spoken Language Processing.Stroudsburg,USA:Association for Computational Linguistics,2002:901-904.
［28］OCH F J.Giza++:training of statistical translation models［EB/OL］.［2017-12-25］.http://www.fjoch.com/GIZA++.html.
［29］PAPINENI K,ROUKOS S,WARD T,et al.BLEU:a method for automatic evaluation of machine translation［C］//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Stroudsburg,USA:Association for Computational Linguistics,2002:311-318.

选择文件类型/文献管理软件名称

选择包含的内容

基于释义信息的维汉机器翻译系统融合研究

Research of Uyghur-Chinese Machine Translation System Combination Based on Paraphrase Information

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于释义信息的维汉机器翻译系统融合研究

Research of Uyghur-Chinese Machine Translation System Combination Based on Paraphrase Information

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价