基于双语短语约束的交互式机器翻译方法

徐萍,叶娜,吴闯,张桂平

PDF(6456 KB)
PDF(6456 KB)
中文信息学报 ›› 2018, Vol. 32 ›› Issue (9) : 1-10.
机器翻译

基于双语短语约束的交互式机器翻译方法

  • 徐萍,叶娜,吴闯,张桂平
作者信息 +

Interactive Machine Translation Based on Bilingual Phrase Constraints

  • XU Ping, YE Na, WU Chuang, ZHANG Guiping
Author information +
History +

摘要

交互式机器翻译(Interactive Machine Translation,IMT)是一种通过机器翻译系统与译员之间的相互作用指导计算机解码并改善输出译文质量的技术。目前主流的IMT方法使用译员确定的前缀作为唯一约束指导解码,交互方式受限,交互效率低。该文从交互方式和解码算法两个方面对IMT方法进行改进。在交互方式方面,允许译员译前从短语译项列表中为源语言短语选择正确译项。该文还提出了基于短语表的多样性排序算法,来提高短语候选译项的多样性,并根据译员的翻译认知过程设计交互界面,改善译员在翻译过程中的用户体验。在解码算法方面,将双语短语与前缀一同作为约束参与指导解码过程,提高翻译假设评价和过滤的准确性。在LDC汉英平行语料上进行了人工评测,实验结果表明该方法较传统的IMT方法能够减轻译员的认知负担,减少翻译时间,提升翻译效率。

Abstract

Interactive machine translation (IMT) is a technology which guides the MT decoder and improves the output quality through interactions with the translator. This paper improves the IMT method from two aspects of interaction mode and decoding algorithm. In terms of interaction mode,the translators are allowed to select the correct translation of source phrases from the phrase table before translation. A re-ranking algorithm is proposed to improve the diversity of the phrase translation options,and an interation interface is designed according to the cognitive process of the translator to improve the user experience. In terms of decoding algorithm,the bilingual phrases are taken as constraints together with the prefix to guide decoding and improve the accuracy of translation hypotheses evaluation and filtration. Experimentation with real users is conducted on the Chinese-English LDC corpora. Results show that compared with the traditional IMT method,our method can reduce the user cognitive burden and the translation time,thus improving the translation efficiency.

关键词

交互式机器翻译 / 双语短语 / 短语译项 / 多样性 / 解码

Key words

interactive machine translation / bilingual phrase / phrase translation option / diversity / decoding

引用本文

导出引用
徐萍,叶娜,吴闯,张桂平. 基于双语短语约束的交互式机器翻译方法. 中文信息学报. 2018, 32(9): 1-10
XU Ping, YE Na, WU Chuang, ZHANG Guiping. Interactive Machine Translation Based on Bilingual Phrase Constraints. Journal of Chinese Information Processing. 2018, 32(9): 1-10

参考文献

[1] 宗成庆. 统计机器翻译[M].北京:电子工业出版社,2012:13-14.
[2] 叶娜,张桂平,韩亚冬,等. 从计算机辅助翻译到协同翻译[J].中文信息学报,2012,26(6):1-10.
[3] Och FJ,Zens R,Ney H. Efficient Search for Interactive Statistical Machine Translation[C]//Proceedings of the 10th Conference on European Chapter of the Association for Computational Linguistics. 2003:387-393.
[4] Civera J,Vilar J M,Cubel E,et al. From machine translation to computer assisted translation using finite-state models[C]//Proceedings of EMNLP 2004,2004:349-356.
[5] Tomás J,Casacuberta F. Statistical phrase-based models for interactive computer-assisted translation[C]//Proceedings of the International Conference on ACL 2006,2006:835-841.
[6] González-Rubio J,Ortiz-Martínez D,Benedí JM,et al. Interactive machine translation using hierarchical translation models[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing,2013:244-254.
[7] Peris ,Domingo M,Casacuberta F. Interactive neural machine translation[J].Computer Speech and Language,2017,45:201-220.
[8] Wuebker J,Green S,DeNero J,et al. Models and inference for prefix-constrained machine translation[C]//Proceedings of the Meeting of the Association for Computational Linguistics,2016:66-75
[9] Nepveu L,Lapalme G,Langlais P,et al. Adaptive language and translation models for interactive machine translation[C]//Proceedings of the 9th EMNLP,2004:190-197.
[10] Bender O,Hasan S,Vilar D,et al. Comparison of generation strategies for interactive machine translation[C]//Proceedings of the 10th EAMT,2005:33-40.
[11] Cai D F,Zhang H,Ye N. Improvements in statistical phrase-based interactive machine translation[C]//Proceedings of the International Conference on Asian Language Processing,2013:91-94.
[12] Koehn P,Tsoukala C,Saintamand H. Refinements to interactive translation prediction based on search graphs[C]//Proceedings of ACL 2014,2014:574-578.
[13] Green S,Wang S,Chuang J,et al. Human effort and machine learnability in computer aided translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2014:1225-1236.
[14] Azadi F,Khadivi S. Improved search strategy for interactive predictions in computer-assisted translation[C]//Proceedings of MT Summit XV,2015:319-332.
[15] Ye N,Zhang G P,Cai D F. Interactive-predictive machine translation based on syntactic constraints of prefix[C]//Proceedings of the 26th International Conference on Computational Linguistics,2016.
[16] González-Rubio J,Martinez D O,Casacuberta F,et al. Beyond prefix-based interactive translation prediction[J].Fundamenta Informaticae,2004,65(3):86-98.
[17] Foster G,Isabell P,Plamondon P. Target-text mediated interactive machine translation[J].Machine Translation,1997,12(1):175-194.
[18] Esteban J,Lorenzo J,Lapalme G,et al. TransType2:An innovative computer-assisted translation system[C]//Proceedings of the ACL on Interactive Poster and Demonstration Sessions,2004,1:94-97.
[19] Green S,Chuang J,Heer J,et al. Predictive translation memory:A mixed-initiative system for human language translation[C]//Proceedings of the ACM Symposium on User Interface Software and Technology,2014:177-187.
[20] Ye N,Fu Y T,Zhang G P,et al. Improving interactive machine translation via multiple positive constraints[C]//Proceedings of the International Conference on Asian Language Processing,2016:5-8.
[21] Cheng S,Huang S,Chen H,et al. PRIMT:a pick-revise framework for interactive machine translation[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2016:1240-1249.
[22] Barrachina S,Bender O,Casacuberta F,et al. Statistical approaches to computer - assisted translation[J].Computational Linguistics,2009 ,35(1):3-28.
[23] Berger AL,Brown PF,Pietra SAD,et al. Language translation apparatus and method of using context-based translation models[P].United States Patent No. 5510981,April.
[24] Tomás J,Casacuberta F. Statistical machine translation decoding using target word reordering[J].Computer Science,204,3138:734-743.
[25] Alabau V,Leiva L A,Ortiz-Martínez D,et al. User evaluation of interactive machine translation systems[C]//Proceedings of the 16th EAMT Conference,2012.
[26] Papineni K,Roukos S,Ward T,et al. BLEU:a method for automatic evaluation of machine translation[C]//Proceedings of the Meeting on Association for Computational Linguistics,2002,4(4):311-318.

基金

国家自然科学基金(61402299)
PDF(6456 KB)

710

Accesses

0

Citation

Detail

段落导航
相关文章

/