计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240600098-9.doi: 10.11896/jsjkx.240600098
李永辉, 叶娜, 白宇, 张桂平
LI Yonghui, YE Na, BAI Yu, ZHANG Guiping
摘要： 现有的神经机器翻译方法在处理专利文本中的复杂长句时仍然面临挑战。首先对专利文本中的复杂长句进行了定量化定义,并针对其翻译过程中存在的术语漏译、错译以及句子结构错译的问题提出了融入术语信息和依存位置编码的神经机器翻译模型。该模型将被约束的术语向量化集成到编码器和解码器的注意力模块以及输出层中,并在位置编码处融合依存位置编码缓解长距离依赖问题。实验表明,所提模型相对于其他几个基线模型在术语翻译成功率和复杂长句整体翻译性能上均有显著提升。
中图分类号:
| [1]JIN Y H.Research on a Hybrid Strategy Patent Machine Translation System [J].Computer Engineering and Applications,2012,48(4):29-32. [2]HU R F.A prepositional phrase automatic recognition strategy for Chinese English patent machine translation [J].Language and Writing Applications,2015(1):136-144. [3]LI H Z,ZHAO K,HU R F,etc.A Chinese English machine translation fusion system for the patent field [J].Intelligence Engineering,2017,3(3):105-115. [4]PARK C,JUNG Y J,KIM K,et al.KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019[C]//Proceedings of the 6th Workshop on Asian Translation.2019:81-89. [5]WANG D,HTUN O.Goku’s Participation in WAT 2020[C]//Proceedings of the 7th Workshop on Asian Translation.2020:135-141. [6]GARCIA X,BANSAL Y,CHERRY C,et al.The unreasonable effectiveness of few-shot learning for machine translation[C]//Proceedings of the 40th International Conference on Machine Learning.PMLR,2023. [7]ZHU W H,LIU H Y,DONG Q X,et al.Multilingual machine translation with large language models:Empirical results and analysis[J]. arXiv:2304.04675,2023. [8]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J].arXiv:1706.03762,2017. [9]MOHAMED S A,ELSAYED A A,HASSAN Y F,et al.Neural machine translation:past,present,and future[J].Neural Computing and Applications,2021,33:15919-15931. [10]GOTO I.Overview of the Patent Translation Task at the NTCIR-9 Workshop[J].Proceedings of NTCIR-9,2011,2011:559-578. [11]HOKAMP C,LIU Q.Lexically Constrained Decoding for Se-quence Generation Using Grid Beam Search[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).2017:1535-1546. [12]POST M,VILAR D.Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long Papers).2018:1314-1324. [13]HU J E,KHAYRALLAH H,CULKIN R,et al.Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting[C]//Proceedings of NAACL-HLT.2019:839-850. [14]ZHANG J,LUAN H,SUN M,et al.Neural machine translation with explicit phrase alignment[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2021,29:1001-1010. [15]SONG K,ZHANG Y,YU H,et al.Code-Switching for Enhancing NMT with Pre-Specified Translation[C]//Proceedings of NAACL-HLT.2019:449-459. [16]DINU G,MATHUR P,FEDERICO M,et al.Training NeuralMachine Translation to Apply Terminology Constraints[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:3063-3068. [17]MICHON E,CREGO J M,SENELLART J.Integrating domain terminology into neural machine translation[C]//Proceedings of the 28th International Conference on Computational Linguistics.2020:3925-3937. [18]YOU X D,YANG H X,CHEN H T,etc. Research on Machine Translation of New Energy Patents Integrating Terminological Information [J].Chinese Journal of Information Science,2021,35(12):76-83. [19]WANG S,LI P,TAN Z,et al.A Template-based Method for Constrained Neural Machine Translation[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.2022:3665-3679. [20]WANG X,TU Z,XIONG D,et al.Translating Phrases in Neural Machine Translation[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.2017:1421-1431. [21]XU H,VAN GENABITH J,XIONG D,et al.Learning Source Phrase Representations for Neural Machine Translation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:386-396. [22]CHEN G,CHEN Y,LI V O K.Lexically constrained neural ma-chine translation with explicit alignment guidance[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:12630-12638. [23]CHEN K,WANG R,UTIYAMA M,et al.Syntax-directed at-tention for neural machine translation[C]//Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence.2018:4792-4799. [24]BASTINGS J,TITOV I,AZIZ W,et al.Graph ConvolutionalEncoders for Syntax-aware Neural Machine Translation[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.2017:1957-1967. [25]DEGUCHI H,TAMURA A,NINOMIYA T.Dependency-based self-attention for transformer NMT[C]//Proceedings of the International Conference on Recent Advances in Natural Language Processing(RANLP 2019).2019:239-246. [26]SHIV V L,QUIRK C.Novel positional encodings to enable tree-based transformers[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems.2019:12081-12091. [27]MA C,TAMURA A,UTIYAMA M,et al.Improving neuralmachine translation with neural syntactic distance[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long and Short Papers).2019:2032-2037. [28]WANG X,TU Z,WANG L,et al.Self-Attention with Structural Position Representations[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:1403-1409. [29]XIE Y,WANG W,DU M,et al.Transformer with Syntactic Position Encoding for Machine Translation[C]//Proceedings of the International Conference on Recent Advances in Natural Language Processing(RANLP 2021).2021:1536-1544. [30]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.2002:311-318. [31]MANNING C D,SURDEANU M,BAUER J,et al.The Stanford CoreNLP natural language processing toolkit[C]//Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics:System Demonstrations.2014:55-60. [32]CHURCH K W.Word2Vec[J].Natural Language Engineering,2017,23(1):155-162. [33]VOITA E,SENNRICH R,TITOV I.The Bottom-up Evolution of Representations in the Transformer:A Study with Machine Translation and Language Modeling Objectives[C]//2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing.Association for Computational Linguistics(ACL),2019:4387-4397. [34]PASCUAL D,EGRESSY B,MEISTER C,et al.A Plug-and-Play Method for Controlled Text Generation[C]//Findings of the Association for Computational Linguistics:EMNLP 2021.2021:3973-3997. [35]NEISHI M,YOSHINAGAN.On the relation between positioninformation and sentence length in neural machine translation[C]//Proceedings of the 23rd Conference on Computational Natural Language Learning(CoNLL).2019:328-338. [36]KOEHN P,HOANG H,BIRCH A,et al.Moses:Open sourcetoolkit for statistical machine translation[C]//Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions.Association for Computational Linguistics,2007:177-180. [37]TIEDEMANN J.Efficient Word Alignment with Markov Chain Monte Carlo[J].The Prague Bulletin of Mathematical Linguistics,106(1):125-146. [38]OTT M,EDUNOV S,BAEVSKI A,et al.FAIRSEQ:A Fast,Extensible Toolkit for Sequence Modeling[J].NAACL HLT 2019,2019:48. |
|
||
首页