End-to-end Adversarial Learning for Generative Conversational Agents

This paper presents a new adversarial learning method for generative conversational agents (GCA) besides a new model of GCA. Similar to previous works on adversarial learning for dialogue generation, our method assumes the GCA as a generator that aims at fooling a discriminator that labels dialogues as human-generated or machine-generated; however, in our approach, the discriminator performs token-level classification, i.e. it indicates whether the current token was generated by humans or machines. To do so, the discriminator also receives the context utterances (the dialogue history) and the incomplete answer up to the current token as input. This new approach makes possible the end-to-end training by backpropagation. A self-conversation process enables to produce a set of generated data with more diversity for the adversarial training. This approach improves the performance on questions not related to the training data. Experimental results with human and adversarial evaluations show that the adversarial method yields significant performance gains over the usual teacher forcing training.

[1]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[2]  Martin Wattenberg,et al.  Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation , 2016, TACL.

[3]  C·马诗纳,et al.  Identification of intents from query reformulations in search , 2015 .

[4]  Ming Li,et al.  Neural Contextual Conversation Learning with Labeled Question-Answering Pairs , 2016, ArXiv.

[5]  Alan Ritter,et al.  Data-Driven Response Generation in Social Media , 2011, EMNLP.

[6]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[7]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

[8]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with High Levels of Correlation with Human Judgments , 2007, WMT@ACL.

[9]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[10]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[11]  Geoffrey E. Hinton,et al.  Grammar as a Foreign Language , 2014, NIPS.

[12]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[13]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

[14]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[15]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[16]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[17]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[19]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[20]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Marie-Francine Moens,et al.  Deep Embedding for Spatial Role Labeling , 2016, ArXiv.

[22]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[23]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[24]  Marie-Francine Moens,et al.  Learning to Extract Action Descriptions From Narrative Text , 2017, IEEE Transactions on Games.

[25]  David Griol,et al.  Evaluating the Conversational Interface , 2016 .

[26]  Joelle Pineau,et al.  How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation , 2016, EMNLP.

[27]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[28]  Sally A. Applin,et al.  New technologies and mixed-use convergence: How humans and algorithms are adapting to each other , 2015, 2015 IEEE International Symposium on Technology and Society (ISTAS).

[29]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[30]  Joelle Pineau,et al.  A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues , 2016, AAAI.

[31]  Phil Blunsom,et al.  Recurrent Continuous Translation Models , 2013, EMNLP.

[32]  Jakob Grue Simonsen,et al.  A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion , 2015, CIKM.

[33]  Rui Yan,et al.  Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation , 2016, COLING.