Page 300 - 《软件学报》2026年第2期

张建新 等: 依存句法信息增强的完全非自回归翻译 779

[14] Wan F, Li P. A neural machine translation method based on split graph convolutional self-attention encoding. PeerJ Computer Science,
2024, 10: e1886. [doi: 10.7717/PEERJ-CS.1886]
[15] Guo JL, Xu LL, Chen EH. Jointly masked sequence-to-sequence model for non-autoregressive neural machine translation. In: Proc. of the
58th Annual Meeting of the ACL. 2020. 376–385. [doi: 10.18653/V1/2020.ACL-MAIN.36]
[16] Zhang Y, Li ZH, Zhang M. Efficient second-order TreeCRF for neural dependency parsing. In: Proc. of the 58th Annual Meeting of the
Association for Computational Linguistics. 2020. 3295–3305. [doi: 10.18653/V1/2020.ACL-MAIN.302]
[17] Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907, 2017.
[18] Zhang Y, Zhang B, Li ZH, Bao ZY, Li C, Zhang M. SynGEC: Syntax-enhanced grammatical error correction with a tailored GEC-
oriented parser. arXiv:2210.12484, 2022.
[19] Ma XZ, Zhou CT, Li X, Neubig G, Hovy EH. FlowSeq: Non-autoregressive conditional sequence generation with generative flow. In:
Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language
Processing (EMNLP-IJCNLP). Hong Kong: ACL, 2019. 4282–4292. [doi: 10.18653/V1/D19-1437]
[20] Gu JT, Kong X. Fully non-autoregressive neural machine translation: Tricks of the trade. In: Proc. of the 2019 Conf. on Empirical
Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing (EMNLP-IJCNLP). 2021.
120–133. [doi: 10.18653/V1/2021.FINDINGS-ACL.11]
[21] Guo P, Xiao YS, Li JT, Zhang M. RenewNAT: Renewing potential translation for non-autoregressive Transformer. In: Proc. of the 37th
AAAI Conf. on Artificial Intelligence. Washington: AAAI Press, 2023. 12854–12862. [doi: 10.1609/AAAI.V37I11.26511]
[22] Wei BZ, Wang MX, Zhou H, Lin JY, Sun X. Imitation learning for non-autoregressive neural machine translation. In: Proc. of the 57th
Annual Meeting of the Association for Computational Linguistics. Florence: ACL, 2019. 1304–1312. [doi: 10.18653/V1/P19-1125]
[23] Libovický J, Helcl J. End-to-end non-autoregressive neural machine translation with connectionist temporal classification. In: Proc. of the
2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: ACL, 2018. 3016–3021. [doi: 10.18653/V1/D18-1336]
[24] Wang YR, Tian F, He D, Qin T, Zhai CX, Liu TY. Non-autoregressive machine translation with auxiliary regularization. In: Proc. of the
33rd AAAI Conf. on Artificial Intelligence. Honolulu: AAAI Press, 2019. 5377–5384. [doi: 10.1609/AAAI.V33I01.33015377]
[25] Guo JL, Tan X, He D, Qin T, Xu LL, Liu TY. Non-autoregressive neural machine translation with enhanced decoder input. In: Proc. of
the 33rd AAAI Conf. on Artificial Intelligence. Honolulu: AAAI Press, 2019. 3723–3730. [doi: 10.1609/AAAI.V33I01.33013723]
[26] Li F. Research of neural machine translation model and algorithm based on non-autoregressive decoding [MS. Thesis]. Nanning: Guangxi
University, 2024 (in Chinese with English abstract). [doi: 10.27034/d.cnki.ggxiu.2024.000806]
[27] Li K. Research of neuron machine translation based on non-autoregressive method [MS. Thesis]. Chengdu: University of Electronic
Science and Technology of China, 2013 (in Chinese with English abstract). [doi: 10.27005/d.cnki.gdzku.2023.003186]
[28] Cui YF. Research on non-autoregressive machine translation based on curriculum learning and enhancing network [MS. Thesis].
Changsha: Central South University, 2023 (in Chinese with English abstract). [doi: 10.27661/d.cnki.gzhnu.2023.001110]
[29] Qian LH, Zhou H, Bao Y, Wang MX, Qiu L, Zhang WN, Yu Y, Li L. Glancing Transformer for non-autoregressive neural 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. 2021. 1993–2003. [doi: 10.18653/V1/2021.ACL-LONG.155]
[30] Lee J, Mansimov E, Cho K. Deterministic non-autoregressive neural sequence modeling by iterative refinement. In: Proc. of the 2018
Conf. on Empirical Methods in Natural Language Processing. Brussels: ACL, 2018. 1173–1182. [doi: 10.18653/V1/D18-1149]
[31] Jiang H, Cai GY, Tang XL. Improving iteration-based non-autoregressive language model with time step awareness. In: Proc of the 29th
IEEE Int’l Conf. on Parallel and Distributed Systems ICPADS. Ocean Flower Island: IEEE, 2023. 2798–2801. [doi: 10.1109/
ICPADS60453.2023.00385]
[32] Zhao GY, Wang J, Gao SX, Yu ZT. Non-autoregressive neural machine translation with contextual feature integration. Journal of Shaanxi
University of Technology (Natural Science Edition), 2024, 40(3): 44–51, 83 (in Chinese with English abstract). [doi: 10.3969/j.issn.1673-
2944.2024.03.006]
[33] Ziv A, Gat I, Le Lan G, Remez T, Kreuk F, Copet J, Défossez A, Synnaeve G, Adi Y. Masked audio generation using a single non-
autoregressive Transformer. arXiv:2401.04577, 2024.
[34] You WJ, Guo P, Li JT, Chen KH, Zhang M. Efficient domain adaptation for non-autoregressive machine translation. In: Findings of the
Association for Computational Linguistics: ACL 2024. Bangkok: ACL, 2024. 13657–13670. [doi: 10.18653/V1/2024.FINDINGS-ACL.
810]
[35] Li JH, Xiong DY, Tu ZP, Zhu MH, Zhang M, Zhou GD. Modeling source syntax for neural machine translation. In: Proc. of the 55th
Annual Meeting of the Association for Computational Linguistics (Vol.1: Long Papers). Vancouver: ACL, 2017. 688–697. [doi: 10.18653/
V1/P17-1064]
[36] Bastings J, Titov I, Aziz W, Marcheggiani D, Sima’an K. Graph convolutional encoders for syntax-aware neural machine translation. In: