机构名翻译是机器翻译的研究内容之一,在机器翻译任务中机构名翻译的准确度,直接影响着翻译性能。在很多任务上,神经机器翻译性能优于传统的统计机器翻译性能,该文中使用基于transformer神经网络模型与传统的基于短语的统计机器翻译模型和改进后的基于语块的机器翻译模型做了对比试验。实验结果表明,在汉蒙机构名翻译任务上,基于transformer神经网络的汉蒙机构名翻译系统优于传统的基于语块的汉蒙机构名翻译系统,BLEU4值提高了0.039。
Abstract
Organization name translation directly affects translation performance. In this study, a transformer-based neural network model is proposed for this task. Compared with a traditional phrase-based SMT model and an improved block-based MT model, the experimental results show that the transformer NMT increased by 0.039 in terms of BLEU 4 in the Chinese-Mongolian Organization name translation task.
关键词
神经网络 /
汉蒙机器翻译 /
机构名
{{custom_keyword}} /
Key words
neural network /
Chinese-Mongolian machine translation /
organization name
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 乌云塔那.基于神经网络的蒙汉神经机器翻译研究[D].呼和浩特: 内蒙古师范大学硕士学位论文,2018.
[2] Peter F Brown, Stephen A, Della Pietra, et al. The mathematics of statistical machine translation: Parameter estimation [J]. Computational Linguistics, 1993,19(2): 263-311.
[3] Franz Josef Och, Hermann Ney, Discriminative training and maximum entropy models for statistical machine translation [A], ACL2002, 2002: 295-302.
[4] 宗成庆,张霄军.统计机器翻译[M].北京: 电子工业出版社,2011.
[5] 刘群,熊德意,刘洋.基于句法的统计机器翻译研究[C].中文信息处理前沿进展——中国中文信息学会二十五周年学术会议论文集.2006: 416-423.
[6] David Chiang.A hierarchical phrase based model for statistical machine translation[C]//Proceedings of the ACL 2005, 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. University of Michigan, USA. DBLP, 2005.6: 25-30.
[7] Kalchbrenner N,Blunsom P.Recurrent continuous translation models[C]//Preceedings of the EMNLP,2013: 1700-1709.
[8] Sutskever I,Vinyals O,Le Q V.Sequence to sequence learning with neural networks[J].Advances in Neural Information Processing Systems,2014(11): 3104–3112.
[9] Cho K,Van Merri nboer B,Gulcehre C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].Empirical Methods in Natural Language Processing,2014: 1724-1734.
[10] Bahdanau D,Cho K,Bengio Y.Neural machine translation by jointly learning to align and translate[J].arXiv peprint arXiv: 1409,0473,2014.
[11] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of Advances in Neural Information Processing Systems,2017: 5998-6008.
[12] 那顺乌日图.面向机器翻译的蒙古语生成[A].山西大学计算机系.自然语言理解与机器翻译——全国第六届计算语言学联合学术会议论文集, 2001: 7.
[13] 侯宏旭,刘群,那顺乌日图.基于实例的汉蒙机器翻译[J].中文信息学报, 2007, 21(4): 65-72.
[14] 王斯日古楞,斯琴图, 那顺乌日图.基于短语的汉蒙统计机器翻译研究[J].内蒙古大学计算机工程与应用,2010,46(14): 138-142.
[15] 杨萍. 基于双语对齐的汉文-新蒙古文命名实体翻译技术研究[D].呼和浩特: 内蒙古大学硕士学位论文,2015.
[16] 藏丹.基于语块的汉蒙机构名自动翻译研究[D].呼和浩特: 内蒙古师范大学硕士学位论文,2017.
[17] 哈斯高娃.蒙汉神经机器翻译中的未登录词处理研究[D].呼和浩特: 内蒙古师范大学硕士学位论文,2019.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61762072);内蒙古自然科学基金(2016MS0623)
{{custom_fund}}
PDF(2809 KB)
