[1] GEHRING J, AULI M, GRANGIER D, et al. Convolutional sequence to sequence learning[C]//Proceedings of the 34th International Conference on Machine Learning, 2017:1243-1252.
[2] VASWANI A, SHAZEER N M, PARMAR N, et al. Attention is all you need[C]//Proceedings of the Advances in Neural Information Processing Systems, 2017:6000-6010.
[3] GU J, BRADBURY J, XIONG C, et al. Non-autoregressive neural machine translation[C]//Proceedings of the 6th International Conference on Learning Representations, 2018.
[4] LEE J, MANSIMOV E, CHO K. Deterministic non-autoregressive neural sequence modeling by iterative refinement[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 1173-1182.
[5] SHU R, LEE J, NAKAYAMA H, et al. Latent-variable non-autoregressive neural machine translation with deterministic inference using a delta posterior[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020: 8846-8853.
[6] GHAZVININEJAD M, LEVY O, LIU Y, et al. Mask-predict: Parallel decoding of conditional masked language models[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2019: 6111-6120.
[7] KASAI J, CROSS J, GHAZVININEJAD M, et al. Non-autoregressive machine translation with disentangled context transformer[C]//Proceedings of the 37th International Conference on Machine Learning, 2020: 5144-5155.
[8] 肖桐,朱靖波.机器翻译:基础与模型[M].北京:电子工业出版社, 2021:373-374.
[9] XIAO Y, WU L, GUO J,et al. A survey on non-autoregressive generation for neural machine translation and beyond[J]. arXiv preprint arXiv:2204.09269, 2022.
[10] KIM Y, RUSH A M. Sequence-level knowledge distillation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016:1317-1327.
[11] ZHOU C, NEUBIG G, GU J. Understanding knowledge distillation in non-autoregressive machine translation[C]//Proceedings of the 8th International Conference on Learning Representations, 2020.
[12] XU W, MA S, ZHANG D, et al. How does distilled data complexity impact the quality and confidence of non-autoregressive machine translation?[C]//Proceedings of the Findings of the Association for Computational Linguistics, 2021:4392-4400.
[13] ZHOU J, KEUNG P. Improving non-autoregressive neural machine translation with monolingual data[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 1893-1898.
[14] DING L, WANG L, LIU X, et al. Understanding and improving lexical choice in non-autoregressive translation[C]//Proceedings of the 9th International Conference on Learning Representations, 2021.
[15] DING L, WANG L, LIU X, et al. Rejuvenating low-frequency words: Making the most of parallel data in non-autoregressive translation[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021: 3431-3441.
[16] SHAO C, WU X, FENG Y. One reference is not enough: Diverse distillation with reference selection for non-autoregressive translation[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2022:3779-3791.
[17] HUANG F, TAO T, ZHOU H,et al. On the learning of non-autoregressive transformers[C]//Proceedings of the International Conference on Machine Learning, 2022:9356-9376.
[18] LEE J, SHU R, CHO K. Iterative refinement in thecontinuous space for non-autoregressive neural machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020:1006-1015.
[19] STERN M, CHAN W, KIROS J R, et al. Insertion transformer: Flexible sequence generation via insertion operations[C]//Proceedings of the 36th International Conference on Machine Learning, 2019: 5976-5985.
[20] GU J, WANG C, ZHAO J, et al. Levenshtein transformer[C]//Proceedings of the Advances in Neural Information Processing Systems, 2019:11179-11189.
[21] DEVLIN J, CHANG M, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2019: 4171-4186.
[22] GHAZVININEJAD M, LEVY O, ZETTLEMOYER L. Semi-autoregressive training improves mask-predict decoding[J]. arXiv preprint arXiv:2001.08785, 2020.
[23] GUO J, XU L, CHEN E. Jointly masked sequence-to-sequence model for non-autoregressive neural machine translation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 376-385.
[24] DING L, WANG L, WU D, et al. Context-aware cross-attention for non-autoregressive translation[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020:4396-4402.
[25] NOROUZI S, HOSSEINZADEH R, PREZ F, et al. DiMS: Distilling multiple steps of iterative non-autoregressive transformers[J]. arXiv preprint arXiv:2206.02999, 2022.
[26] GENG X, FENG X, QIN B. Learning to rewrite for non-autoregressive neural machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2021:3297-3308.
[27] KASAI J, PAPPAS N, PENG H, et al. Deep encoder, shallow decoder: Reevaluating the speed-quality tradeoff in machine translation[J].arXiv preprint arXiv:2006.10369, 2020.
[28] KAISER , ROY A, VASWANI A, et al. Fast decoding in sequence models using discrete latent variables[C]//Proceedings of the 35th International Conference on Machine Learning, 2018: 2395-2404.
[29] AKOURY N, KRISHNA K, IYYER M. Syntactically supervised transformers for faster neural machine translation[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019: 1269-1281.
[30] BAO Y, HUANG S, XIAO T, et al. Non-autoregressive translation by learning target categorical codes[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2021:5749-5759.
[31] ROY A, VASWANI A, NEELAKANTAN A,et al. Theory and experiments on vector quantized autoencoders[J]. arXiv preprint arXiv:1805.11063, 2018.
[32] BAO Y, ZHOU H, FENG J, et al. Non-autoregressive transformer by position learning[J]. arXiv preprint arXiv:1911.10677, 2019.
[33] RAN Q, LIN Y, LI P, et al. Guiding non-autoregressive neural machine translation decoding with reordering information[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021: 13727-13735.
[34] SONG J, KIM S, YOON S. AligNART: Non-autoregressive neural machine translation by jointly learning to estimate alignment and translate[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2021:1-14.
[35] MA X, ZHOU C, LI X, et al. FlowSeq: Non-autoregressive conditional sequence generation with generative flow[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2019: 4281-4291.
[36] REZENDE D J, MOHAMED S. Variational inference with normalizing flows[C]//Proceedings of the 32nd International Conference on Machine Learning, 2015:1530-1538.
[37] LIBOVICKY｀ J, HELCL J. End-to-end non-autoregressive neural machine translation with connectionist temporal classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 3016-3021.
[38] SAHARIA C, CHAN W, SAXENA S, et al. Non-autoregressive machine translation with latent alignments[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020:1098-1108.
[39] WANG Y, TIAN F, HE D, et al. Non-autoregressivemachine translation with auxiliary regularization[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019: 5377-5384.
[40] SUN Z, LI Z, WANG H, et al. Fast structured decoding for sequence models[C]//Proceedings of the Advances in Neural Information Processing Systems, 2019: 3011-3020.
[41] LIU Y, WAN Y, ZHANG J,et al. Enriching non-autoregressive transformer with syntactic and semantic structures for neural machine translation[C]//Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021:1235-1244.
[42] SHAO C, FENG Y, ZHANG J, et al. Retrieving sequential information for non-autoregressive neural machine translation[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019: 3013-3024.
[43] SHAO C, ZHANG J, FENG Y, et al. Minimizing the bag-of-ngrams difference for non-autoregressive neural machine translation[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020: 198-205.
[44] SHAO C, FENG Y, ZHANG J,et al. Sequence-level training for non-autoregressive neural machine translation[C]//Proceedings of the Computational Linguistics, 2021:891-925.
[45] GHAZVININEJAD M, KARPUKHIN V, ZETTLEMOYER L, et al. Aligned cross entropy for non-autoregressive machine translation[C]//Proceedings of the 37th International Conference on Machine Learning, 2020: 3515-3523.
[46] DU C, TU Z, JIANG J. Order-agnostic cross entropy for non-autoregressive machine translation[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 2849-2859.
[47] WEI B, WANG M, ZHOU H, et al. Imitation learning for non-autoregressive neural machine translation[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019:1304-1312.
[48] LI Z, LIN Z, HE D, et al. Hint-based training for non-autoregressive machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2019: 5707-5712.
[49] TU L, PANG R, WISEMAN S, et al. ENGINE: Energy-Based inference networks for non-autoregressive machine translation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 2819-2826.
[50] GUO J, TAN X, XU L, et al. Fine-tuning by curriculum learning for non-autoregressive neural machine translation[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2020: 7839-7846.
[51] LIU J, REN Y, TAN X, et al. Task-level curriculum learning for non-autoregressive neural machine translation[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence, 2020: 3861-3867.
[52] SUN Z, YANG Y. An EM Approach to Non-autoregressive Conditional Sequence Generation[C]//Proceedings of the 37th International Conference on Machine Learning, 2020: 9249-9258.
[53] HAO Y, HE S, JIAO W, et al. Multi-task learning with shared encoder for non-autoregressive machine translation[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2021: 3989-3996.
[54] GUO J, TAN X, HE D, et al. Non-autoregressive neural machine translation with enhanced decoder input[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019: 3723-3730.
[55] ZHAN J, CHEN Q, CHEN B, et al. Non-autoregressive translation with dependency-aware decoder[J]. arXiv preprint arXiv:2203.16266, 2022.
[56] LI X, MENG Y, YUAN A, et al. LAVA NAT: A non-autoregressive translation model with look-around decoding and vocabulary attention[J]. arXiv preprint arXiv:2002.03084, 2020.
[57] DENG Y, RUSH A M. Sequence-to-lattice models for fast translation[C]//Proceedings of the Association for Computational Linguistics, 2021:3765-3772.
[58] ZHENG Z, ZHOU H, HUANG S, et al. Duplex sequence-to-sequence learning for reversible machine translation[C]//Proceedings of the Advances in Neural Information Processing Systems, 2021:21070-21084.
[59] WANG C, ZHANG J, CHEN H. Semi-autoregressive neural machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018:479-488.
[60] RAN Q, LIN Y, LI P, et al. Learning to recover from multi-modality errors for non-autoregressive neural machine translation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 3059-3069.
[61] KONG X, ZHANG Z, HOVY E H. Incorporating a local translation mechanism into non-autoregressive translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020:1067-1073.
[62] DENG Y, RUSH A M. Cascaded text generation with markov transformers[C]//Proceedings of the Advances in Neural Information Processing Systems, 2020.
[63] QIAN L, ZHOU H, BAO Y, et al. Glancing transformer for non-autoregressive neural machine translation[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021: 1993-2003.
[64] DING L, WANG L, LIU X, et al. Progressive multi-granularity training for non-autoregressive translation[C]//Proceedings of the Association for Computational Linguistics, 2021: 2797-2803.
[65] XIE P, LI Z, HU X. MvSR-NAT: Multi-view subset regularization for non-autoregressive machine translation[J]. arXiv preprint arXiv:2108.08447, 2021.
[66] ZENG C, CHEN J, ZHUANG T, et al. Neighbors are not strangers: Improving non-autoregressive translation under low-frequency lexical constraints[J]. arXiv preprint arXiv:2204.13355, 2022.
[67] BAO Y, ZHOU H, HUANG S, et al. GLAT: Glancing at latent variables for parallel text generation[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022:8398-8409.
[68] HUANG F, ZHOU H, LIU Y, et al. Directed acyclic transformer for non-autoregressive machine translation[C]//Proceedings of the International Conference on Machine Learning, 2022:9410-9428.
[69] HUANG X S, PEREZ F, VOLKOVS M. Improving non-autoregressive translation models without distillation[C]//Proceedings of the International Conference on Learning Representations, 2022.
[70] GU J, KONG X. Fully non-autoregressive neural machine translation: Tricks of the trade[C]//Proceedings of the Association for Computational Linguistics, 2021: 120-133.
[71] HELCL J, HADDOW B, BIRCH A. Non-autoregressive machine translation: Its not as fast as it seems[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2022:1780-1790.
[72] REN Y, RUAN Y, TAN X, et al. FastSpeech: Fast, robust and controllable text to speech[C]//Proceedings of the Advances in Neural Information Processing Systems, 2019:3165-3174.
[73] PENG K, PING W, SONG Z, et al. Non-autoregressive neural text-to-speech[C]//Proceedings of the 37th International Conference on Machine Learning, 2020: 7586-7598.
[74] CHEN N, WATANABE S, VILLALBA J, et al. Listen and fill in the missing letters: non-autoregressive transformer for speech recognition[J]. arXiv preprint arXiv:1911.04908, 2019.
[75] FUJITA Y, WATANABE S, OMACHI M, et al. Insertion-based modeling for end-to-end automatic speech recognition[C]//Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020: 3660-3664.
[76] HIGUCHI Y, WATANABE S, CHEN N, et al. Mask CTC: Non-autoregressive end-to-end ASR with CTC and mask predict[C]//Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020: 3655-3659.
[77] FEI Z. Fast image caption generation with position alignment[J]. arXiv preprint arXiv:1912.06365, 2019.
[78] GAO J, MENG X, WANG S,et al. Masked non-autoregressive image captioning[J]. arXiv preprint arXiv:1906.00717, 2019.
[79] SUSANTO R H, CHOLLAMPATT S, TAN L. Lexically constrained neural machine translation with levenshtein transformer[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020:3536-3543.
[80] LI P, LI L, ZHANG M,et al. Universal conditional masked language pre-training for neural machine translation[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2022.
[81] ZHANG Y, WANG G, LI C,et al. Pointer: Constrained text generation via insertion-based generative pre-training[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020:8649-8670.