Neural Response Generation via GAN with an Approximate Embedding Layer

This paper presents a Generative Adversarial Network (GAN) to model single-turn short-text conversations, which trains a sequence-to-sequence (Seq2Seq) network for response generation simultaneously with a discriminative classifier that measures the differences between human-produced responses and machine-generated ones. In addition, the proposed method introduces an approximate embedding layer to solve the non-differentiable problem caused by the sampling-based output decoding procedure in the Seq2Seq generative model. The GAN setup provides an effective way to avoid noninformative responses (a.k.a “safe responses”), which are frequently observed in traditional neural response generators. The experimental results show that the proposed approach significantly outperforms existing neural response generation models in diversity metrics, with slight increases in relevance scores as well, when evaluated on both a Mandarin corpus and an English corpus.

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

[2]  Jörg Tiedemann,et al.  OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles , 2016, LREC.

[3]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

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

[5]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[6]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[7]  Hang Li,et al.  Convolutional Neural Network Architectures for Matching Natural Language Sentences , 2014, NIPS.

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

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

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

[11]  Xuan Liu,et al.  Multi-view Response Selection for Human-Computer Conversation , 2016, EMNLP.

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

[13]  Mirella Lapata,et al.  Vector-based Models of Semantic Composition , 2008, ACL.

[14]  Bo Chen,et al.  Mechanism-Aware Neural Machine for Dialogue Response Generation , 2017, AAAI.

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

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

[17]  Joelle Pineau,et al.  Bootstrapping Dialog Systems with Word Embeddings , 2014 .

[18]  Sridhar Mahadevan,et al.  Generative Multi-Adversarial Networks , 2016, ICLR.

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

[20]  Vasile Rus,et al.  A Comparison of Greedy and Optimal Assessment of Natural Language Student Input Using Word-to-Word Similarity Metrics , 2012, BEA@NAACL-HLT.

[21]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[22]  Bowen Zhou,et al.  Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation , 2016, AAAI.

[23]  Wei-Ying Ma,et al.  Topic Aware Neural Response Generation , 2016, AAAI.

[24]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

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

[26]  Bowen Wu,et al.  Ranking Responses Oriented to Conversational Relevance in Chat-bots , 2016, COLING.