篇章中的同一实体经常会呈现出不同的表述,形成一系列复杂的指代关系,这给篇章翻译带来了很大的挑战。该文重点探索指代消解和篇章神经机器翻译的融合方案,首先为指代链设计相应的指代表征;其次使用软约束和硬约束两种方法在翻译系统中实现指代信息的融合。该文建议的方法分别在英语-德语和中文-英语语言对上进行了实验,实验结果表明,相比于同期最好的句子级翻译系统,该方法能使翻译性能获得明显提升。此外,在英语-德语的代词翻译质量的专门评估中,准确率也有显著提升。
Abstract
The same entity in a document often occurs in multiple expressions, forming a series of complex referential relations. To deal with this challenge to Document-level translation, this paper focuses on integrating reference resolution into Document-level machine translation. First, we design the reference representation for the reference chain; Then, we introduce a new translation mechanism to fuse reference representation by combining soft constraint and hard constraint. Experiments on English-German and Chinese-English datasets show that compared with the best sentence-level translation system, our methods can significantly improve translation performance. In addition, experiments show the our methods lead to a strong improvement in the task of evaluating the translation quality of English-German pronouns.
关键词
指代表征 /
神经机器翻译 /
篇章级机器翻译
{{custom_keyword}} /
Key words
reference representation /
neural machine translation /
document-level machine translation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[C]//Proceedings of the ICLR, 2015: 1-15.
[2] WU Y, SCHUSTER M, CHEN Z, et al. Googles neural machine translation system: Bridging the gap between human and machine translation[J/OL]. arXiv preprint arXiv: 1609.08144, 2016.
[3] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[4] MARUF S, SALEH F, HAFFARI G. A survey on document-level neural machine translation: Methods and evaluation[J]. ACM Computing Surveys, 2021,54(2): 1-36.
[5] TIEDEMANNJ, SCHERRER Y. Neural machine translation with extended context[C]//Proceedings of the 3rd Workshop on Discourse in Machine Translation, 2017: 82-92.
[6] WANGL, TU Z, WAY A, et al. Exploiting cross-sentence context for neural machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 2826-2831.
[7] TU Z, LIU Y, SHI S, et al. Learning to remember translation history with a continuous cache[J]. Transactions of the Association for Computational Linguistics, 2018: 407-420.
[8] ZHAHG J, LUAN H, SUN M, et al. Improving the transformer translation model with document-level context[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 533-542.
[9] VOITA E, SERDYUKOV P, SENNRICH R, et al. Context-aware neural machine translation learns anaphora resolution[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1264-1274.
[10] MA S, ZHANG D, ZHOU M. A simple and effective unified encoder for document-level machine translation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 3505-3511.
[11] 孔芳,周国栋,朱巧明等.指代消解综述[J].计算机工程, 2010,36(008): 33-36.
[12] LE NAGARD R, KOEHN P. Aiding pronoun translation with co-reference resolution[C]//Proceedings of the Joint 5th Workshop on Statistical Machine Translation and Metrics MATR. Association for Computational Linguistics, 2010: 252-261.
[13] HARDMEIER C, FEDERICO M. Modelling pronominal anaphora in statistical machine translation[C]//Proceedings of International Workshop on Spoken Language Translation, 2012: 283-289.
[14] OHTANI T, KAMIGAITO H, NAGATA M, et al. Context-aware neural machine translation with coreference information[C]//Proceedings of the 4th Workshop on Discourse in Machine Translation, 2019: 45-50.
[15] TONG Y, ZHENG J, ZHU H, et al. A document-level neural machine translation model with dynamic caching guided by theme-rheme information[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020: 4385-4395.
[16] WISEMAN S, RUSH A M, SHIEBER S M. Learning global features for coreference resolution[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016: 994-1004.
[17] CLARK K, MANNING C D. Deep reinforcement learning for mention-ranking coreference models[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 2256-2262.
[18] LEE K, HE L, LEWIS M, et al. End-to-end neural coreference resolution[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 188-197.
[19] JOSHI M, CHEN D, LIU Y, et al. Spanbert: Improving pre-training by representing and predicting spans[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 64-77.
[20] LIB, LIU H, WANG Z, et al. Does multi-encoder help? A case study on context-aware neural machine translation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 3512-3518.
[21] LAMPLE G, BALLESTEROS M, SUBRAMANIAN S, et al. Neural architectures for named entity recognition[C]//Proceedings of the Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, 2016: 260-270.
[22] SENNRICH R, HADDOW B, BIRCH A. Neural machine translation of rare words with subword units[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 1715-1725.
[23] KINGMA D P, BA J. Adam: A method for stochastic optimization[J/OL]. arXiv preprint arXiv: 1412.6980, 2014.
[24] FREITAG M, ALONAIZAN Y. Beam search strategies for neural machine translation[C]//Proceedings of the 1st Workshop on Neural Machine Translation, 2017: 56-60.
[25] 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.
[26] MLLER M, RIOS A, VOITA E, et al. A large-scale test set for the evaluation of context-aware pronoun translation in neural machine translation[C]//Proceedings of the 3rd Conference on Machine Translation, 2018: 61-72.
[27] BAO G, ZHANG Y, TENG Z, et al. G-transformer for document-level machine translation[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 3442-3455.
[28] LIU Y, GU J, GOYAL N, et al. Multilingual denoising pre-training for neural machine translation[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 726-742.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61976148)
{{custom_fund}}
PDF(2493 KB)
