Unsupervised Learning of Interpretable Dialog Models

Recently several deep learning based models have been proposed for end-to-end learning of dialogs. While these models can be trained from data without the need for any additional annotations, it is hard to interpret them. On the other hand, there exist traditional state based dialog systems, where the states of the dialog are discrete and hence easy to interpret. However these states need to be handcrafted and annotated in the data. To achieve the best of both worlds, we propose Latent State Tracking Network (LSTN) using which we learn an interpretable model in unsupervised manner. The model defines a discrete latent variable at each turn of the conversation which can take a finite set of values. Since these discrete variables are not present in the training data, we use EM algorithm to train our model in unsupervised manner. In the experiments, we show that LSTN can help achieve interpretability in dialog models without much decrease in performance compared to end-to-end approaches.

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

[2]  David Vandyke,et al.  Conditional Generation and Snapshot Learning in Neural Dialogue Systems , 2016, EMNLP.

[3]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

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

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

[6]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[7]  Marilyn A. Walker,et al.  A trainable generator for recommendations in multimodal dialog , 2003, INTERSPEECH.

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

[9]  J. Koenderink.  Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[10]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Dongho Kim,et al.  POMDP-based dialogue manager adaptation to extended domains , 2013, SIGDIAL Conference.

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

[14]  Roberto Pieraccini,et al.  A stochastic model of human-machine interaction for learning dialog strategies , 2000, IEEE Trans. Speech Audio Process..

[15]  Oriol Vinyals,et al.  Neural Discrete Representation Learning , 2017, NIPS.

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

[17]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[18]  Maxine Eskénazi,et al.  Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation , 2018, ACL.

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

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

[21]  Tsung-Hsien Wen,et al.  Latent Intention Dialogue Models , 2017, ICML.

[22]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

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

[24]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[25]  Christopher D. Manning,et al.  Key-Value Retrieval Networks for Task-Oriented Dialogue , 2017, SIGDIAL Conference.