欢迎在文章下方评论，建议用电脑看
Andrew Ng 曾说，不管是已经工作还是在读学生，每周坚持读几篇不错的 paper，长此以往做下去能力会有一个质的飞跃。
(1) An actor Critic algorithm for sequence prediction
(1)SeqGAN
(3)MaliGAN
现在的课题，分为goal-driven dialog system 和open domain dialog system。
这个来说，现在主要研究的是end to end的模型。
(1)Learning End-to-End Goal-Oriented Dialog
(3)End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
(3)A Network-based End-to-End Trainable Task-oriented Dialogue System
(5)End To End task Completion neural dialogue systems
(1)Adversarial Learning for Neural Dialogue Generation
(2)Deep Reinforcement Learning for Dialogue Generation
(1)Topic aware neural response generation
(2)Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
(3)A knowledge Grounded neural conversation model
