神经机器翻译前沿综述

[1] Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning[J] . Ronald J. Williams.Machine Learning . 1992 (3)

[2] A Learning Algorithm for Continually Running Fully Recurrent Neural Networks [J]. NEURAL COMPUTATION, 1989, 1 (02) : 270 - 280

[3] Fast structured decoding for sequence models .2 Sun Z,Li Z,Wang H,et al. Procedings of Advances in Neural Information Processing Systems . 2019

[4] Training neural machine translation using word embedding-based loss .2 Chousa K,Sudoh K,Nakamura S. . 2018

[5] Bi-directional differentiable input reconstruction for low-resource neural machine translation .2 Niu X,Xu W,Carpuat M. Proceedings of the 2019Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies . 2019

[6] Modeling coherence for discourse neural machine translation .2 Xiong H,He Z,Wu H,et al. Proceedings of the AAAI Conference on Artificial Intelligence . 2019

[7] Contextual parameter generation for universal neural machine translation .2 Platanios E A,SachanM,Neubig G,et al. Proceedings of the 2018Conference on Empirical Methods in Natural Language Processing . 2018

[8] Fast decoding in sequence models using discrete latent variables .2 Kaiser L,Bengio S,Roy A,et al. Proceedings of the 35th International Conference on Machine Learning . 2018

[9] Discourse-aware neural rewards for coherent text generation .2 Bosselut A,Celikyilmaz A,He X,et al. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies . 2018

[10] Deterministic non-autoregressive neural sequence modeling by iterative refinement .2 Lee J,Mansimov E,Cho K. Proceedings of the 2018Conference on Empirical Methods in Natural Language Processing . 2018

[1] Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning[J] . Ronald J. Williams.Machine Learning . 1992 (3)

[2] A Learning Algorithm for Continually Running Fully Recurrent Neural Networks [J]. NEURAL COMPUTATION, 1989, 1 (02) : 270 - 280

[3] Fast structured decoding for sequence models .2 Sun Z,Li Z,Wang H,et al. Procedings of Advances in Neural Information Processing Systems . 2019

[4] Training neural machine translation using word embedding-based loss .2 Chousa K,Sudoh K,Nakamura S. . 2018

[5] Bi-directional differentiable input reconstruction for low-resource neural machine translation .2 Niu X,Xu W,Carpuat M. Proceedings of the 2019Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies . 2019

[6] Modeling coherence for discourse neural machine translation .2 Xiong H,He Z,Wu H,et al. Proceedings of the AAAI Conference on Artificial Intelligence . 2019

[7] Contextual parameter generation for universal neural machine translation .2 Platanios E A,SachanM,Neubig G,et al. Proceedings of the 2018Conference on Empirical Methods in Natural Language Processing . 2018

[8] Fast decoding in sequence models using discrete latent variables .2 Kaiser L,Bengio S,Roy A,et al. Proceedings of the 35th International Conference on Machine Learning . 2018

[9] Discourse-aware neural rewards for coherent text generation .2 Bosselut A,Celikyilmaz A,He X,et al. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies . 2018

[10] Deterministic non-autoregressive neural sequence modeling by iterative refinement .2 Lee J,Mansimov E,Cho K. Proceedings of the 2018Conference on Empirical Methods in Natural Language Processing . 2018