DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior such as standard normal distribution, thereby restricting the generated responses to a relatively simple (e.g., unimodal) scope. In this paper, we propose DialogWAE, a conditional Wasserstein autoencoder~(WAE) specially designed for dialogue modeling. Unlike VAEs that impose a simple distribution over the latent variables, DialogWAE models the distribution of data by training a GAN within the latent variable space. Specifically, our model samples from the prior and posterior distributions over the latent variables by transforming context-dependent random noise using neural networks and minimizes the Wasserstein distance between the two distributions. We further develop a Gaussian mixture prior network to enrich the latent space. Experiments on two popular datasets show that DialogWAE outperforms the state-of-the-art approaches in generating more coherent, informative and diverse responses.

[1]  Matt J. Kusner,et al.  GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution , 2016, ArXiv.

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

[3]  Colin Cherry,et al.  A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU , 2014, WMT@ACL.

[4]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[5]  Jung-Woo Ha,et al.  NSML: Meet the MLaaS platform with a real-world case study , 2018, ArXiv.

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

[7]  Regina Barzilay,et al.  Style Transfer from Non-Parallel Text by Cross-Alignment , 2017, NIPS.

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

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

[10]  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.

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

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

[13]  Xiaoyu Shen,et al.  Improving Variational Encoder-Decoders in Dialogue Generation , 2018, AAAI.

[14]  Jung-Woo Ha,et al.  NSML: A Machine Learning Platform That Enables You to Focus on Your Models , 2017, ArXiv.

[15]  Maxine Eskénazi,et al.  Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders , 2017, ACL.

[16]  Eric P. Xing,et al.  Nonparametric Variational Auto-Encoders for Hierarchical Representation Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[18]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

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

[20]  Bernhard Schölkopf,et al.  Wasserstein Auto-Encoders , 2017, ICLR.

[21]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[22]  Masaru Kitsuregawa,et al.  Modeling Situations in Neural Chat Bots , 2017, ACL.

[23]  Gunhee Kim,et al.  A Hierarchical Latent Structure for Variational Conversation Modeling , 2018, NAACL.

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

[25]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

[26]  Xiaoyu Shen,et al.  DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset , 2017, IJCNLP.

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

[28]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[29]  Alexander M. Rush,et al.  Adversarially Regularized Autoencoders , 2017, ICML.

[30]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

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

[32]  Zhen Xu,et al.  Neural Response Generation via GAN with an Approximate Embedding Layer , 2017, EMNLP.

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