文档级神经机器翻译综述

doi:10.13328/j.cnki.jos.007217

微信服务号

微信订阅号

2025年5月11日 11:21 星期日

首页 > 过刊浏览>2025年第36卷第1期 >152-183. DOI:10.13328/j.cnki.jos.007217

PDF HTML阅读 XML下载导出引用引用提醒

文档级神经机器翻译综述
DOI:
                        10.13328/j.cnki.jos.007217
                    
CSTR:
                        32375.14.jos.007217
                    
作者:
                        吕星林吕星林
苏州大学 计算机科学与技术学院, 江苏 苏州 215006
在期刊界中查找
在百度中查找
在本站中查找
李军辉李军辉
苏州大学 计算机科学与技术学院, 江苏 苏州 215006
在期刊界中查找
在百度中查找
在本站中查找
陶仕敏陶仕敏
华为翻译中心, 北京 100080
在期刊界中查找
在百度中查找
在本站中查找
杨浩杨浩
华为翻译中心, 北京 100080
在期刊界中查找
在百度中查找
在本站中查找
张民张民
苏州大学 计算机科学与技术学院, 江苏 苏州 215006
在期刊界中查找
在百度中查找
在本站中查找

                    
作者单位:
作者简介:
通讯作者:
中图分类号:
基金项目:国家自然科学基金(62036004); 江苏高校优势学科建设工程

Survey on Document-level Neural Machine Translation

Author:

Lü Xing-Lin
Lü Xing-Lin
School of Computer Science and Technology, Soochow University, Suzhou 215006, China
在期刊界中查找
在百度中查找
在本站中查找
LI Jun-Hui
LI Jun-Hui
School of Computer Science and Technology, Soochow University, Suzhou 215006, China
在期刊界中查找
在百度中查找
在本站中查找
TAO Shi-Min
TAO Shi-Min
Huawei Translation Service Center, Beijing 100080, China
在期刊界中查找
在百度中查找
在本站中查找
YANG Hao
YANG Hao
Huawei Translation Service Center, Beijing 100080, China
在期刊界中查找
在百度中查找
在本站中查找
ZHANG Min
ZHANG Min
School of Computer Science and Technology, Soochow University, Suzhou 215006, China
在期刊界中查找
在百度中查找
在本站中查找

Affiliation:

Fund Project:

摘要

图/表

访问统计

参考文献 [197]

相似文献

引证文献

资源附件

文章评论

摘要:

机器翻译(machine translation, MT)研究旨在构建一个自动转换系统, 将给定源语言序列自动地转换为具有相同语义的目标语言序列. 由于机器翻译广阔的应用场景, 使其成为自然语言理解领域乃至人工智能领域的一个重要的研究方向. 近年来, 端到端的神经机器翻译(neural machine translation, NMT)方法显著超越了统计机器翻译(statistical machine translation, SMT)方法, 成为目前机器翻译研究的主流方法. 然而, 神经机器翻译系统通常以句子为翻译单位, 在面向文档的翻译场景中, 将文档中每个句子独立地进行翻译, 会因脱离文档的篇章语境引起一些篇章级的错误, 如词语错翻、句子间不连贯等. 因此将文档级的信息融入到翻译的过程中去解决跨句的篇章级错误是更加自然和合理的做法, 文档级的神经机器翻译(document-level neural machine translation, DNMT)的目标正是如此, 成为机器翻译研究的热门方向. 调研了近年来在文档级神经机器翻译研究方向的主要工作, 从篇章评测方法、使用的数据集和模型方法等方面系统地对当前研究工作进行了归纳与阐述, 目的是帮助研究者们快速了解文档级神经机器翻译研究现状以及未来的发展和研究方向. 同时在文中也阐述了在文档级神经机器翻译的一些展望、困难和挑战, 希望能带给研究者们一些启发.

关键词:神经机器翻译;Transformer模型;文档上下文;篇章评测

Abstract:

Machine translation (MT) aims to build an automatic translating system to transform a given sequence in the source language into another target language sequence that shares identical semantic information. MT has been an important research direction in natural language processing and artificial intelligence fields for its widely applied scenarios. In recent years, the performance of neural machine translation (NMT) greatly surpasses that of statistical machine translation (SMT), becoming the mainstream method in MT research. However, NMT generally takes the sentence as the translated unit, and in document-level translation scenarios, some discourse errors such as the mistranslation of words and incoherent sentences may occur due to the separation with discourse context if the sentence is translated independently. Therefore, incorporating document-level information into the procedure of translation may be a more reasonable and natural way to solve discourse errors. This conforms with the goal of document-level neural machine translation (DNMT) and has been a popular direction in MT research. This study reviews and summarizes works in DNMT research in terms of discourse evaluation methods, datasets and models applied, and other aspects to help the researchers efficiently learn the research status and further directions of DNMT. Meanwhile, this study also introduces the prospect and some challenges in DNMT, hoping to bring some inspiration to researchers.

Key words:neural machine translation;Transformer;document-level context;discourse evaluation

参考文献

[1] Sutskever I, Vinyals O, Le QV. Sequence to sequence learning with neural networks. In: Ghahramani Z, et al. eds. Proc. of the 27th Int’l Conf. on Neural Information Processing Systems. Cambridge: MIT Press, 2014. 3104–3112.

[2] Kalchbrenner N, Blunsom P. Recurrent continuous translation models. In: Proc. of the 2013 Conf. on Empirical Methods in Natural Language Processing. Seattle: ACL, 2013. 1700–1709.

[3] Cho K, van Merrienboer B, Gulcehre G, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proc. of the 2014 Conf. on Empirical Methods in Natural Language Processing. Doha: ACL, 2014. 1724–1734. [doi: 10.3115/v1/D14-1179]

[4] Meng FD, Lu ZD, Wang MX, Li H, Jiang WB, Liu Q. Encoding source language with convolutional neural network for machine translation. In: Proc. of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th Int’l Joint Conf. on Natural Language Processing (Vol. 1: Long Papers). Beijing: ACL, 2015. 20–30. [doi: 10.3115/v1/P15-1003]

[5] Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN. Convolutional sequence to sequence learning. In: Proc. of the 34th Int’l Conf. on Machine Learning. Sydney: JMLR.org, 2017. 1243–1252.

[6] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: Proc. of the 3rd Int’l Conf. on Learning Representations. San Diego: ICLR, 2015.

[7] Luong T, Pham H, Manning CD. Effective approaches to attention-based neural machine translation. In: Proc. of the 2015 Conf. on Empirical Methods in Natural Language Processing. Lisbon: ACL, 2015. 1412–1421. [doi: 10.18653/v1/D15-1166]

[8] Yang ZC, Hu ZT, Deng YT, Dyer C, Smola A. Neural machine translation with recurrent attention modeling. In: Proc. of the 15th Conf. of the European Chapter of the Association for Computational Linguistics. Valencia: ACL, 2017. 383–387.

[9] Ranzato MA, Chopra S, Auli M, Zaremba W. Sequence level training with recurrent neural networks. In: Proc. of the 4th Int’l Conf. on Learning Representations. San Juan: ICLR, 2016.

[10] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proc. of the 31st Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 6000–6010.

[11] Tiedemann J. Context adaptation in statistical machine translation using models with exponentially decaying cache. In: Proc. of the 2010 Workshop on Domain Adaptation for Natural Language Processing. Uppsala: Association for Computational Linguistics, 2010. 8–15.

[12] Gong ZX, Zhang M, Zhou GD. Cache-based document-level statistical machine translation. In: Proc. of the 2011 Conf. on Empirical Methods in Natural Language Processing. Edinburgh: ACL, 2011. 909–919.

[13] Hardmeier C, Nivre J, Tiedemann J. Document-wide decoding for phrase-based statistical machine translation. In: Proc. of the 2012 Joint Conf. on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Jeju Island: Association for Computational Linguistics, 2012. 1179–1190.

[14] Stymne S, Tiedemann J, Hardmeier C, Nivre J. Statistical machine translation with readability constraints. In: Proc. of the 19th Nordic Conf. of Computational Linguistics. Oslo: Linköping University Electronic Press, 2013. 375–386.

[15] Xiong DY, Ding Y, Zhang M, Tan CL. Lexical chain based cohesion models for document-level statistical machine translation. In: Proc. of the 2013 Conf. on Empirical Methods in Natural Language Processing. Seattle: ACL, 2013. 1563–1573.

[16] Pearlmutter BA. Learning state space trajectories in recurrent neural networks. Neural Computation, 1989, 1(2): 263–269.

[17] Wang LY, Tu ZP, Way A, Liu Q. Exploiting cross-sentence context for neural machine translation. In: Proc. of the 2017 Conf. on Empirical Methods in Natural Language Processing. Copenhagen: ACL, 2017. 2826–2831. [doi: 10.18653/v1/D17-1301]

[18] Tu ZP, Liu Y, Shi SM, Zhang T. Learning to remember translation history with a continuous cache. Trans. of the Association for Computational Linguistics, 2018, 6: 407–420.

[19] Zhang JC, Luan HB, Sun MS, Zhai FF, Xu JF, Zhang M, Liu Y. Improving the transformer translation model with document-level context. In: Proc. of the 2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: ACL, 2018. 533–542. [doi: 10.18653/v1/D18-1049]

[20] Tan X, Zhang LY, Xiong DY, Zhou GD. Hierarchical modeling of global context for document-level neural machine translation. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: ACL, 2019. 1576–1585. [doi: 10.18653/v1/D19-1168]

[21] Yang ZX, Zhang JC, Meng FD, Gu SH, Feng Y, Zhou J. Enhancing context modeling with a query-guided capsule network for document-level translation. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: ACL, 2019. 1527–1537. [doi: 10.18653/v1/D19-1164]

[22] Macé V, Servan C. Using whole document context in neural machine translation. In: Proc. of the 16th Int’l Conf. on Spoken Language Translation. Hong Kong: ACL, 2019.

[23] Kang XM, Zhao Y, Zhang JJ, Zong CQ. Dynamic context selection for document-level neural machine translation via reinforcement learning. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. ACL, 2020. 2242–2254.

[24] Xu HF, Xiong DY, Van Genabith J, Liu QH. Efficient context-aware neural machine translation with layer-wise weighting and input-aware gating. In: Proc. of the 29th Int’l Joint Conf. on Artificial Intelligence. Yokohama: IJCAI, 2021. 544.

[25] Fernandes P, Yin K, Neubig G, Martins AFT. Measuring and increasing context usage in context-aware machine translation. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. ACL, 2021. 6467–6478.

[26] Bawden R, Sennrich R, Birch A, Haddow B. Evaluating discourse phenomena in neural machine translation. In: Proc. of the 2018 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans: ACL, 2018. 1304–1313. [doi: 10.18653/v1/N18-1118]

[27] Maruf S, Haffari G. Document context neural machine translation with memory networks. In: Proc. of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne: ACL, 2018. 1275–1284. [doi: 10.18653/v1/P18-1118]

[28] Zheng ZX, Yue X, Huang SJ, Chen JJ, Birch A. Towards making the most of context in neural machine translation. In: Proc. of the 29th Int’l Joint Conf. on Artificial Intelligence. Yokohama: IJCAI, 2021. 551.

[29] Bao GS, Zhang Y, Teng ZY, Chen BX, Luo WH. G-Transformer for document-level machine translation. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. ACL, 2021. 3442–3455.

[30] Sun ZW, Wang MX, Zhou H, Zhao CQ, Huang SJ, Chen JJ, Li L. Rethinking document-level neural machine translation. In: Proc. of the 2022 Findings of the Association for Computational Linguistics. Dublin: ACL, 2022. 3537–3548. [doi: 10.18653/v1/2022.findings-acl.279]

[31] Kang XM, Zhao Y, Zhang JJ, Zong CQ. Enhancing lexical translation consistency for document-level neural machine translation. ACM Trans. on Asian and Low-resource Language Information Processing, 2021, 21(3): 59.

[32] Lyu XL, Li JH, Gong ZX, Zhang M. Encouraging lexical translation consistency for document-level neural machine translation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. ACL, 2021. 3265–3277.

[33] Papineni K, Roukos S, Ward T, Zhu WJ. BLEU: A method for automatic evaluation of machine translation. In: Proc. of the 40th Annual Meeting of the Association for Computational Linguistics. Philadelphia: ACL, 2002. 311–318. [doi: 10.3115/1073083.1073135]

[34] Werlen LM, Belis AP. Validation of an automatic metric for the accuracy of pronoun translation (APT). In: Proc. of the 3rd Workshop on Discourse in Machine Translation. Copenhagen: ACL, 2017. 17–25. [doi: 10.18653/v1/W17-4802]

[35] Jiang YC, Liu TY, Ma SM, Zhang DD, Yang J, Huang HY, Sennrich R, Cotterell R, Sachan M, Zhou M. BlonDe: An automatic evaluation metric for document-level machine translation. In: Proc. of the 2022 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Seattle: ACL, 2022. 1550–1565. [doi: 10.18653/v1/2022.naacl-main.111]

[36] Maruf S, Saleh F, Haffari G. A survey on document-level neural machine translation: Methods and evaluation. ACM Computing Surveys, 2021, 54(2): 45.

[37] Giménez J, Màrquez L, Comelles E, Castellón I, Arranz V. Document-level automatic MT evaluation based on discourse representations. In: Proc. of the 5th Joint Workshop on Statistical Machine Translation and MetricsMATR. Uppsala: ACL, 2010. 333–338.

[38] Vela M, Tan LL. Predicting machine translation adequacy with document embeddings. In: Proc. of the 10th Workshop on Statistical Machine Translation. Lisbon: ACL, 2015. 402–410. [doi: 10.18653/v1/W15-3051]

[39] Junczys-Dowmunt M. Microsoft translator at WMT 2019: Towards large-scale document-level neural machine translation. In: Proc. of the 4th Conf. on Machine Translation. Florence: ACL, 2019. 225–233. [doi: 10.18653/v1/W19-5321]

[40] Rysová K, Rysová M, Musil T, Poláková L, Bojar O. A test suite and manual evaluation of document-level NMT at WMT19. In: Proc. of the 4th Conf. on Machine Translation. Florence: ACL, 2019. 455–463. [doi: 10.18653/v1/W19-5352]

[41] Kuang SH, Xiong DY. Fusing recency into neural machine translation with an inter-sentence gate model. In: Proc. of the 27th Int’l Conf. on Computational Linguistics. Santa Fe: ACL, 2018. 607–617.

[42] Kuang SH, Xiong DY, Luo WH, Zhou GD. Modeling coherence for neural machine translation with dynamic and topic caches. In: Proc. of the 27th Int’l Conf. on Computational Linguistics. Santa Fe: ACL, 2018. 596–606.

[43] Yu L, Sartran L, Stokowiec W, Ling W, Kong LP, Blunsom P, Dyer C. Better document-level machine translation with Bayes’ rule. Trans. of the Association for Computational Linguistics, 2020, 8: 346–360.

[44] Xiong H, He ZJ, Wu H, Wang HF. Modeling coherence for discourse neural machine translation. In: Proc. of the 33rd AAAI Conf. on Artificial Intelligence. Honolulu: AAAI, 2019. 7338–7345. [doi: 10.1609/aaai.v33i01.33017338]

[45] Tan X, Zhang LY, Zhou GD. Coupling context modeling with zero pronoun recovering for document-level natural language generation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. ACL, 2021. 2530–2540.

[46] Yamagishi H, Komachi M. Improving context-aware neural machine translation with target-side context. In: Proc. of the 16th Int’l Conf. of the Pacific Association for Computational Linguistics. Hanoi: PACLING, 2019. 112–122.

[47] Miculicich L, Ram D, Pappas N, Henderson J. Document-level neural machine translation with hierarchical attention networks. In: Proc. of the 2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: ACL, 2018. 2947–2954. [doi: 10.18653/v1/D18-1325]

[48] Zhang L, Zhang T, Zhang HB, Yang BS, Ye W, Zhang SK. Multi-hop transformer for document-level machine translation. In: Proc. of the 2021 Conf. of the North American Chapter of the Association for Computational Linguistics. ACL, 2021. 3953–3963.

[49] Li B, Liu H, Wang ZY, Jiang YF, Xiao T, Zhu JB, Liu TR, Li CL. Does multi-encoder help? A case study on context-aware neural machine translation. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. ACL, 2020. 3512–3518.

[50] Li YC, Li JH, Jiang J, Tao SM, Yang H, Zhang M. P-Transformer: Towards better document-to-document neural machine translation. IEEE/ACM Trans. on Audio, Speech, and Language Processing, 2023, 31: 3859–3870.

[51] Maruf S, Martins AF, Haffari G. Selective attention for context-aware neural machine translation. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: ACL, 2019. 3092–3102. [doi: 10.18653/v1/N19-1313]

[52] Wong KY, Maruf S, Haffari G. Contextual neural machine translation improves translation of cataphoric pronouns. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. ACL, 2020. 5971–5978.

[53] Ma SM, Zhang DD, Zhou M. A simple and effective unified encoder for document-level machine translation. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. ACL, 2020. 3505–3511.

[54] Lei YK, Ren YQ, Xiong DY. CoDoNMT: Modeling cohesion devices for document-level neural machine translation. In: Proc. of the 29th Int’l Conf. on Computational Linguistics. Gyeongju: Int’l Committee on Computational Linguistics, 2022. 5205–5216.

[55] Yun H, Hwang Y, Jung K. Improving context-aware neural machine translation using self-attentive sentence embedding. In: Proc. of the 34th AAAI Conf. on Artificial Intelligence. New York: AAAI, 2020. 9498–9506. [doi: 10.1609/aaai.v34i05.6494]

[56] Mino H, Ito H, Goto I, Yamada I, Tokunaga T. Effective use of target-side context for neural machine translation. In: Proc. of the 28th Int’l Conf. on Computational Linguistics. Barcelona: International Committee on Computational Linguistics, 2020. 4483–4494.

[57] Chen JX, Li X, Zhang JR, Zhou CL, Cui JW, Wang B, Su JS. Modeling discourse structure for document-level neural machine translation. In: Proc. of the 1st Workshop on Automatic Simultaneous Translation. Seattle: ACL, 2020. 30–36.

[58] Maruf S, Martins AF, Haffari G. Contextual neural model for translating bilingual multi-speaker conversations. In: Proc. of the 3rd Conf. on Machine Translation: Research Papers. Brussels: ACL, 2018. 101–112. [doi: 10.18653/v1/W18-6311]

[59] Wang XY, Weston J, Auli M, Jernite Y. Improving conditioning in context-aware sequence to sequence models. arXiv:1911.09728, 2019.

[60] Yin K, Fernandes P, Pruthi D, Chaudhary A, Martins AF, Neubig G. Do context-aware translation models pay the right attention? In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. ACL, 2021. 788–801.

[61] Voita E, Serdyukov P, Sennrich R, Titov I. Context-aware neural machine translation learns anaphora resolution. In: Proc. of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne: ACL, 2018. 1264–1274. [doi: 10.18653/v1/P18-1117]

[62] Voita E, Sennrich R, Titov I. When a good translation is wrong in context: Context-aware machine translation improves on deixis, ellipsis, and lexical cohesion. In: Proc. of the 57th Annual Meeting of the Association for Computational Linguistics. Florence: ACL, 2019. 1198–1212. [doi: 10.18653/v1/P19-1116]

[63] Voita E, Sennrich R, Titov I. Context-aware monolingual repair for neural machine translation. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: ACL, 2019. 877–886. [doi: 10.18653/v1/D19-1081]

[64] Xu MZ, Li LY, Wong DF, Liu Q, Chao LS. Document graph for neural machine translation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. ACL, 2021. 8435–8448.

[65] Snover M, Dorr B, Schwartz R, Micciulla L, Makhoul J. A study of translation edit rate with targeted human annotation. In: Proc. of the 7th Conf. of the Association for Machine Translation in the Americas: Technical Papers. Cambridge: Association for Machine Translation in the Americas, 2006. 223–231.

[66] Banerjee S, Lavie A. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Proc. of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization. Ann Arbor: ACL, 2005. 65–72.

[67] Lin CY. ROUGE: A package for automatic evaluation of summaries. In: Proc. of the Text Summarization Branches Out. Barcelona: ACL, 2004. 74–81.

[68] Cai XY, Xiong DY. A test suite for evaluating discourse phenomena in document-level neural machine translation. In: Proc. of the 2nd Int’l Workshop of Discourse Processing. Suzhou: ACL, 2020. 13–17.

[69] Guillou L, Hardmeier C, Nakov P, Stymne S, Tiedemann J, Versley Y, Cettolo M, Webber B, Popescu-Belis A. Findings of the 2016 WMT shared task on cross-lingual pronoun prediction. In: Proc. of the 1st Conf. on Machine Translation: Vol. 2, Shared Task Papers. Berlin: ACL, 2016. 525–542. [doi: 10.18653/v1/W16-2345]

[70] Loáiciga S, Stymne S, Nakov P, Hardmeier C, Tiedemann J, Cettolo M, Versley Y. Findings of the 2017 DiscoMT shared task on cross-lingual pronoun prediction. In: Proc. of the 3rd Workshop on Discourse in Machine Translation. Copenhagen: ACL, 2017. 1–16. [doi: 10.18653/v1/W17-4801]

[71] Hardmeier C, Federico M. Modelling pronominal anaphora in statistical machine translation. In: Proc. of the 7th Int’l Workshop on Spoken Language Translation: Papers. Paris: IWSLT, 2010. 283–289.

[72] Hardmeier C, Nakov P, Stymne S, Tiedemann J, Versley Y, Cettolo M. Pronoun-focused MT and cross-lingual pronoun prediction: Findings of the 2015 DiscoMT shared task on pronoun translation. In: Proc. of the 2nd Workshop on Discourse in Machine Translation. Lisbon: ACL, 2015. 1–16. [doi: 10.18653/v1/W15-2501]

[73] Guillou L, Hardmeier C. PROTEST: A test suite for evaluating pronouns in machine translation. In: Proc. of the 10th Int’l Conf. on Language Resources and Evaluation. Portorož: European Language Resources Association, 2016. 636–643.

[74] Müller M, Rios A, Voita E, Sennrich R. A large-scale test set for the evaluation of context-aware pronoun translation in neural machine translation. In: Proc. of the 3rd Conf. on Machine Translation: Research Papers. Brussels: ACL, 2018. 61–72. [doi: 10.18653/v1/W18-6307]

[75] Jwalapuram P, Joty S, Temnikova I, Nakov P. Evaluating pronominal anaphora in machine translation: An evaluation measure and a test suite. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: ACL, 2019. 2964–2975. [doi: 10.18653/v1/D19-1294]

[76] Shimazu S, Takase S, Nakazawa T, Okazaki N. Evaluation dataset for zero pronoun in Japanese to English translation. In: Proc. of the 12th Language Resources and Evaluation Conf. Marseille: European Language Resources Association, 2020. 3630–3634.

[77] Wong BTM, Kit C. Extending machine translation evaluation metrics with lexical cohesion to document level. In: Proc. of the 2012 Joint Conf. on Empirical Methods in Natural Language Processing. Jeju Island: ACL, 2012. 1060–1068.

[78] Gong ZX, Zhang M, Zhou GD. Document-level machine translation evaluation with gist consistency and text cohesion. In: Proc. of the 2nd Workshop on Discourse in Machine Translation. Lisbon: ACL, 2015. 33–40. [doi: 10.18653/v1/W15-2504]

[79] Lapata M, Barzilay R. Automatic evaluation of text coherence: Models and representations. In: Proc. of the 19th Int’l Joint Conf. on Artificial Intelligence. Edinburgh: Morgan Kaufmann Publishers Inc., 2005. 1085–1090.

[80] Liang YL, Meng FD, Chen YF, Xu JA, Zhou J. Modeling bilingual conversational characteristics for neural chat translation. In: Proc. of the 59th Annual Meeting of Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. ACL, 2021. 5711–5724.

[81] Itagaki M, Aikawa T, He XD. Automatic validation of terminology translation consistenscy with statistical method. In: Proc. of the 2007 Machine Translation Summit XI: Papers. Ottawa: MTSummit, 2007. 269–274.

[82] Guillou L. Analysing lexical consistency in translation. In: Proc. of the 2013 Workshop on Discourse in Machine Translation. Sofia: ACL, 2013. 10–18.

[83] Reeder F. Measuring MT adequacy using latent semantic analysis. In: Proc. of the 7th Conf. of the Association for Machine Translation in the Americas: Technical Papers. Cambridge: Association for Machine Translation in the Americas, 2006. 176–184.

[84] Hajlaoui N, Popescu-Belis A. Assessing the accuracy of discourse connective translations: Validation of an automatic metric. In: Proc. of the 14th Int’l Conf. on Intelligent Text Processing and Computational Linguistics. Karlovasi: Springer, 2013. 236–247.

[85] Tiedemann J, Scherrer Y. Neural machine translation with extended context. In: Proc. of the 3rd Workshop on Discourse in Machine Translation. Copenhagen: ACL, 2017. 82–92. [doi: 10.18653/v1/W17-4811]

[86] Jean S, Lauly S, Firat O, Cho K. Does neural machine translation benefit from larger context? arXiv:1704.05135, 2017.

[87] 亢晓勉, 宗成庆. 基于篇章结构多任务学习的神经机器翻译. 软件学报, 2022, 33(10): 3806–3818. http://www.jos.org.cn/1000-9825/6316.htm

Kang XM, Zong CQ. Neural machine translation based on multi-task learning of discourse structure. Ruan Jian Xue Bao/Journal of Software, 2022, 33(10): 3806–3818 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6316.htm

[88] Tan X, Zhang LY, Kong F, Zhou GD. Towards discourse-aware document-level neural machine translation. In: Proc. of the 31st Int’l Joint Conf. on Artificial Intelligence. Vienna: IJCAI, 2022. 4383–4389.

[89] Lin ZH, Feng MW, dos Santos CN, Yu M, Xiang B, Zhou BW, Bengio Y. A structured self-attentive sentence embedding. In: Proc. of the 5th Int’l Conf. on Learning Representations. Toulon: ICLR, 2017.

[90] Devlin J, Chang MW, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: ACL, 2019. 4171–4186. [doi: 10.18653/v1/N19-1423]

[91] 孔芳, 葛海柱, 周国栋. 篇章视角的汉语零指代语料库构建. 软件学报, 2021, 32(12): 3782–3801. http://www.jos.org.cn/1000-9825/6119.htm

Kong F, Ge HZ, Zhou GD. Corpus construction for Chinese zero anaphora from discourse perspective. Ruan Jian Xue Bao/Journal of Software, 2021, 32(12): 3782–3801 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6119.htm

[92] Hwang Y, Yun H, Jung K. Contrastive learning for context-aware neural machine translation using coreference information. In: Proc. of the 6th Conf. on Machine Translation. ACL, 2021. 1135–1144.

[93] Lupo L, Dinarelli M, Besacier L. Divide and rule: Effective pre-training for context-aware multi-encoder translation models. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics. Dublin: ACL, 2022. 4557–4572. [doi: 10.18653/v1/2022.acl-long.312]

[94] Merkel M. Consistency and variation in technical translation: A study of translators’ attitudes. In: Proc. of Unity in Diversity, Translation Studies Conf. 1996. 137–149.

[95] Carpuat M. One translation per discourse. In: Proc. of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions. Boulder: ACL, 2009. 19–27.

[96] Ture F, Oard DW, Resnik P. Encouraging consistent translation choices. In: Proc. of the 2012 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Montréal: ACL, 2012. 417–426.

[97] Lyu XL, Li JH, Tao SM, Yang H, Qin Y, Zhang M. Modeling consistency preference via lexical chains for document-level neural machine translation. In: Proc. of the 2022 Conf. on Empirical Methods in Natural Language Processing. Abu Dhabi: ACL, 2022. 6312–6326. [doi: 10.18653/v1/2022.emnlp-main.424]

[98] Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks? In: Proc. of the 27th Int’l Conf. on Neural Information Processing Systems. Montreal: MIT Press, 2014. 3320–3328.

[99] Liu YH, Gu JT, Goyal N, Li X, Edunov S, Ghazvininejad M, Lewis M, Zettlemoyer L. Multilingual denoising pre-training for neural machine translation. Trans. of the Association for Computational Linguistics, 2020, 8: 726–742.

[100] Li LY, Jiang X, Liu Q. Pretrained language models for document-level neural machine translation. arXiv:1911.03110, 2019.

[101] Sugiyama A, Yoshinaga N. Context-aware decoder for neural machine translation using a target-side document-level language model. In: Proc. of the 2021 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 2021. 5781–5791.

[102] OpenAI. GPT-4 technical report. arXiv:2303.08774, 2023.

[103] Xue LT, Constant N, Roberts A, Kale M, Al-Rfou R, Siddhant A, Barua A, Raffel C. mT5: A massively multilingual pre-trained text-to-text transformer. In: Proc. of the 2021 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 2021. 483–498.

[104] Sanh V, Webson A, Raffel C, et al. Multitask prompted training enables zero-shot task generalization. In: Proc. of the 10th Int’l Conf. on Learning Representations. ICLR, 2022.

[105] Wang LY, Lyu CY, Ji TB, Zhang ZR, Yu D, Shi SM, Tu ZP. Document-Level machine translation with large language models. In: Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore: ACL, 2023. 16646–16661.

[106] Karpinska M, Iyyer M. Large language models effectively leverage document-level context for literary translation, but critical errors persist. In: Proc. of the 8th Conf. on Machine Translation. Singapore: ACL, 2023. 419–451. [doi: 10.18653/v1/2023.wmt-1.41]

[107] Zhu JH, Xia YC, Wu LJ, He D, Qin T, Zhou WG, Li HQ, Liu TY. Incorporating BERT into neural machine translation. In: Proc. of the 8th Int’l Conf. on Learning Representations. Addis Ababa: ICLR, 2023.

[108] Guo ZY, Le Nguyen M. Document-level neural machine translation using BERT as context encoder. In: Proc. of the 1st Conf. of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th Int’l Joint Conf. on Natural Language Processing: Student Research Workshop. Suzhou: ACL, 2020. 101–107.

[109] Donato D, Yu L, Dyer C. Diverse pretrained context encodings improve document translation. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. ACL, 2021. 1299–1311.

[110] Zhang JQ, Zhao Y, Saleh M, Liu PJ. PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization. In: Proc. of the 37th Int’l Conf. on Machine Learning. ICML, 2020. 11328–11339.

[111] Wu XQ, Xia YC, Zhu JH, Wu LJ, Xie SF, Qin T. A study of BERT for context-aware neural machine translation. Machine Learning, 2022, 111(3): 917–935.

[112] Sennrich R, Haddow B, Birch A. Improving neural machine translation models with monolingual data. In: Proc. of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin: ACL, 2016. 86–96. [doi: 10.18653/v1/P16-1009]

[113] Zhang JJ, Zong CQ. Exploiting source-side monolingual data in neural machine translation. In: Proc. of the 2016 Conf. on Empirical Methods in Natural Language Processing. Austin: ACL, 2016. 1535–1545. [doi: 10.18653/v1/D16-1160]

[114] Farajian MA, Lopes AV, Martins AFT, Maruf S, Haffari G. Findings of the WMT 2020 shared task on chat translation. In: Proc. of the 5th Conf. on Machine Translation. ACL, 2020. 65–75.

[115] Sulubacak U, Caglayan O, Grönroos SA, Rouhe A, Elliott D, Specia L, Tiedemann J. Multimodal machine translation through visuals and speech. Machine Translation, 2020, 34(2): 97–147.

[116] Bérard A, Pietquin O, Servan C, Besacier L. Listen and translate: A proof of concept for end-to-end speech-to-text translation. In: Proc. of NIPS Workshop on End-to-end Learning for Speech and Audio Processing. Barcelona, 2016.

[117] Weiss RJ, Chorowski J, Jaitly N, Wu YH, Chen ZF. Sequence-to-sequence models can directly translate foreign speech. In: Proc. of the 18th Annual Conf. of the Int’l Speech Communication Association. Stockholm: Interspeech, 2017. 2625–2629.

[118] Calixto I, Liu Q, Campbell N. Doubly-attentive decoder for multi-modal neural machine translation. In: Proc. of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver: ACL, 2017. 1913–1924. [doi: 10.18653/v1/P17-1175]

[119] Huang PY, Liu F, Shiang SR, Oh J, Dyer C. Attention-based multimodal neural machine translation. In: Proc. of the 1st Conf. on Machine Translation. Berlin: ACL, 2016. 639–645. [doi: 10.18653/v1/W16-2360]

[120] Wang X, Wu JW, Chen JK, Li L, Wang YF, Wang WY. VaTeX: A large-scale, high-quality multilingual dataset for video-and-language research. In: Proc. of the 2019 IEEE/CVF Int’l Conf. on Computer Vision. Seoul: IEEE, 2019. 4580–4590.

[121] Aharoni R, Johnson M, Firat O. Massively multilingual neural machine translation. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics Human Language Technologies. Minneapolis: ACL, 2019. 3874–3884. [doi: 10.18653/v1/N19-1388]

[122] Dabre R, Chu CH, Kunchukuttan A. A survey of multilingual neural machine translation. ACM Computing Surveys, 2020, 53(5): 99.

[123] Zhang B, Bapna A, Johnson M, Dabirmoghaddam A, Arivazhagan N, Firat O. Multilingual document-level translation enables zero-shot transfer from sentences to documents. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics. Dublin: ACL, 2022. 4176–4192. [doi: 10.18653/v1/2022.acl-long.287]

[124] Zhu WH, Liu HY, Dong QX, Xu JJ, Huang SJ, Kong LP, Chen JJ, Li L. Multilingual machine translation with large language models: Empirical results and analysis. arXiv:2304.04675, 2023.