计算机科学 ›› 2022, Vol. 49 ›› Issue (1): 271-278.doi: 10.11896/jsjkx.201200094
宁秋怡, 史小静, 段湘煜, 张民
NING Qiu-yi, SHI Xiao-jing, DUAN Xiang-yu, ZHANG Min
摘要： 近年来,神经机器翻译的译文质量取得了显著的进步,但是其在训练过程中严重依赖平行的双语句子对。然而对于电子商务领域来说,平行资源是稀缺的,此外,文化的不同导致产品信息表达存在风格差异。为了解决这两个问题,提出了一种基于风格感知的无监督领域适应算法,该算法在互训练方法中充分利用电子商务单语数据,同时引入拟知识蒸馏的方法处理风格差异。通过获取电商产品数据信息构建非平行双语语料,基于该语料以及中英新闻平行语料进行多组实验,结果表明,相比各种无监督领域适应方法,该算法显著提高了翻译质量,较最强的基线系统提高了约5个BLEU点。此外,将该算法在Ted,Law和Medical OPUS 3类数据上进一步拓展应用,均取得了更佳的翻译效果。
中图分类号:
| [1]CURREY A,BARONE A V M,HEAFIELD K.Copied Monolingual Data Improves Low-Resource Neural Machine Translation[C]//Proceedings of the Second Conference on Machine Translation.Denmark:Association for Computational Linguistics,2017:148-156. [2]SENNRICH R,HADDOW B,BIRCH A.Improving Neural Machine Translation Models with Monolingual Data[C]//Procee-dings of the 54th Annual Meeting of the Association for Computational Linguistics.Germany:Association for Computational Linguistics,2016:86-96. [3]DOU Z Y,HU J J,ANASTASOPOULOS A,et al.Unsuper-vised domain adaptation for neural machine translation with domain-aware feature embeddings[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Proces-sing and the 9th International Joint Conference on Natural Language Processing.Hong Kong:Association for Computational Linguistics,2019:1417-1422. [4]HU J,XIA M,NEUBIG G,et al.Domain Adaptation of Neural Machine Translation by Lexicon Induction[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics.Italy:Association for Computational Linguistics,2019:2989-3001. [5]SHEN Y,LEONARD D,PAVEL P,et al.Word-based Domain Adaptation for Neural Machine Translation[C]//Proceedings of the International Workshop on Spoken Language Translation.Belgium,2019. [6]ZHANG Z,LIU S,LI M,et al.Joint Training for Neural Machine Translation Models with Monolingual Data[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.USA:AAAI Press,2018:555-562. [7]HE D,XIA Y,QIN T,et al.Dual Learning for Machine Translation[J].Advances in Neural Information Processing Systems 29:Annual Conference on Neural Information Processing Systems,2016(12):820-828. [8]ZHEN Y,WEI C,FENG W,et al.Unsupervised Domain Adaptation for Neural Machine Translation[C]//24th International Conference on Pattern Recognition.China:IEEE Computer So-ciety,2018:338-343. [9]ZHENG Z,ZHOU H,HUANG S,et al.Mirror-generative neural machine translation[C]//8th International Conference on Learning Representations.Ethiopia:ICLR,2020. [10]NIU X,RAO S,CARPUAT M.Multi-task neural models fortranslating between styles within and across languages[C]//Proceedings of the 27th International Conference on Computational Linguistics.USA:Association for Computational Linguistics,2018:1008-1020. [11]KOEHN P,OCH F J,MARCU D.Statistical Phrase-BasedTranslation[C]//Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics.Canada:Association for Computational Linguistics,2013:48-54. [12]ARTETXE M,LABAKA G,AGIRRE E.An Effective Ap-proach to Unsupervised Machine Translation[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics.Italy:Association for Computational Linguistics,2019:194-203. [13]ARTETXE M,LABAKA G,AGIRRE E.Unsupervised Statisti-cal Machine Translation[C]//Proceedings of the 2018 Confe-rence on Empirical Methods in Natural Language Processing.Belgium:Association for Computational Linguistics,2018:3623-3642. [14]LUONG T,PHAM H,MANNING C D.Effective Approaches to Attention-based Neural Machine Translation[C]//Procee-dings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon.Portugal:Association for Computational Linguistics,2015:1412-1421. [15]ASHISH V,NOAM S,NIKI P,et al.Attention is all you need[C]//Advances in Neural Information Processing Systems 30.USA:NIPS,2017:5998-6008. [16]YOON K,ALEXANDER M R.Sequence-Level Knowledge Distillation[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.USA:Association for Computational Linguistics,2016:1317-1327. [17]SUTSKEVER I,ORIOL V,QUOC V L.Sequence to sequence learning with neural networks[C]//Advances in Neural Information Processing Systems 27.Canada:NIPS,2014:3104-3112. [18]SENNRICH R,HADDOW B,BIRCH A.Neural MachineTranslation of Rare Words with Subword Units[C]//Procee-dings of the 54th Annual Meeting of the Association for Computational Linguistics.Germany:Association for Computational Linguistics,2016:1715-1725. [19]PAPINENI K,ROUKOS S,WARD T,et al.Bleu:a method for automatic evaluation of machine translation [C]//Proceedings of the 40th annual meeting of the Association for Computational Linguistics.USA:Association for Computational Linguistics,2002:311-318. [20]CHRIS D,VICTOR C,NOAH A S.A Simple,Fast,and Effective Reparameterization of IBM Model 2[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics.USA:Association for Computational Linguistics,2013:644-648. [21]HU D M,ZHU C G,HU C,et al.Multilingual Text EmotionalAnalysis with Pre-trained Model and Attention Mechanism[J].Journal of Chinese Mini-Micro Computer Systems,2020,41(2):278-284. [22]QIAO B W,LI J H.Neural Machine Translation CombiningSource Semantic Roles[J].Computer Science,2020,47(2):163-168. |
| [1] | 宋杰, 梁美玉, 薛哲, 杜军平, 寇菲菲. 基于无监督集群级的科技论文异质图节点表示学习方法 Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level 计算机科学, 2022, 49(9): 64-69. https://doi.org/10.11896/jsjkx.220500196 |
| [2] | 李斌, 万源. 基于相似度矩阵学习和矩阵校正的无监督多视角特征选择 Unsupervised Multi-view Feature Selection Based on Similarity Matrix Learning and Matrix Alignment 计算机科学, 2022, 49(8): 86-96. https://doi.org/10.11896/jsjkx.210700124 |
| [3] | 蔡晓娟, 谭文安. 一种改进的融合相似度和信任度的协同过滤算法 Improved Collaborative Filtering Algorithm Combining Similarity and Trust 计算机科学, 2022, 49(6A): 238-241. https://doi.org/10.11896/jsjkx.210400088 |
| [4] | 董振恒, 任维平, 游新冬, 吕学强. 融入新能源领域术语知识的机器翻译方法 Machine Translation Method Integrating New Energy Terminology Knowledge 计算机科学, 2022, 49(6): 305-312. https://doi.org/10.11896/jsjkx.210500117 |
| [5] | 刘俊鹏, 苏劲松, 黄德根. 融合特定语言适配模块的多语言神经机器翻译 Incorporating Language-specific Adapter into Multilingual Neural Machine Translation 计算机科学, 2022, 49(1): 17-23. https://doi.org/10.11896/jsjkx.210900005 |
| [6] | 于东, 谢婉莹, 谷舒豪, 冯洋. 基于语种关联度课程学习的多语言神经机器翻译 Similarity-based Curriculum Learning for Multilingual Neural Machine Translation 计算机科学, 2022, 49(1): 24-30. https://doi.org/10.11896/jsjkx.210800254 |
| [7] | 侯宏旭, 孙硕, 乌尼尔. 蒙汉神经机器翻译研究综述 Survey of Mongolian-Chinese Neural Machine Translation 计算机科学, 2022, 49(1): 31-40. https://doi.org/10.11896/jsjkx.210900006 |
| [8] | 刘妍, 熊德意. 面向小语种机器翻译的平行语料库构建方法 Construction Method of Parallel Corpus for Minority Language Machine Translation 计算机科学, 2022, 49(1): 41-46. https://doi.org/10.11896/jsjkx.210900012 |
| [9] | 刘创, 熊德意. 多语言问答研究综述 Survey of Multilingual Question Answering 计算机科学, 2022, 49(1): 65-72. https://doi.org/10.11896/jsjkx.210900003 |
| [10] | 吴兰, 王涵, 李斌全. 基于自监督任务最优选择的无监督域自适应方法 Unsupervised Domain Adaptive Method Based on Optimal Selection of Self-supervised Tasks 计算机科学, 2021, 48(6A): 357-363. https://doi.org/10.11896/jsjkx.201000030 |
| [11] | 刘荣, 张宁. 图片分析在电子商务中的应用现状与未来趋势——基于图片视觉和内容特征的研究综述 Application Status and Future Trends of Photo Analysis in E-commerce:A Survey of Research Based on Photo Visual and Content Features 计算机科学, 2021, 48(6A): 137-142. https://doi.org/10.11896/jsjkx.210100017 |
| [12] | 刘小蝶. 基于边界感知的复杂名词短语的识别和转换研究 Recognition and Transformation for Complex Noun Phrases Based on Boundary Perception 计算机科学, 2021, 48(6A): 299-305. https://doi.org/10.11896/jsjkx.200500157 |
| [13] | 郭丹, 唐申庚, 洪日昌, 汪萌. 手语识别、翻译与生成综述 Review of Sign Language Recognition, Translation and Generation 计算机科学, 2021, 48(3): 60-70. https://doi.org/10.11896/jsjkx.210100227 |
| [14] | 马闯, 田青, 孙赫阳, 曹猛, 马廷淮. 基于双重权重偏差建模的无监督域适应 Unsupervised Domain Adaptation Based on Weighting Dual Biases 计算机科学, 2021, 48(2): 217-223. https://doi.org/10.11896/jsjkx.200700028 |
| [15] | 邹承明, 陈德. 高维大数据分析的无监督异常检测方法 Unsupervised Anomaly Detection Method for High-dimensional Big Data Analysis 计算机科学, 2021, 48(2): 121-127. https://doi.org/10.11896/jsjkx.191100141 |
|
||
首页