Learning End-to-End Goal-Oriented Dialog

Traditional dialog systems used in goal-oriented applications require a lot of domain-specific handcrafting, which hinders scaling up to new domains. End-to-end dialog systems, in which all components are trained from the dialogs themselves, escape this limitation. But the encouraging success recently obtained in chit-chat dialog may not carry over to goal-oriented settings. This paper proposes a testbed to break down the strengths and shortcomings of end-to-end dialog systems in goal-oriented applications. Set in the context of restaurant reservation, our tasks require manipulating sentences and symbols, so as to properly conduct conversations, issue API calls and use the outputs of such calls. We show that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations. We confirm those results by comparing our system to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge (Henderson et al., 2014a). We show similar result patterns on data extracted from an online concierge service.

[1]  Milica Gasic,et al.  POMDP-Based Statistical Spoken Dialog Systems: A Review , 2013, Proceedings of the IEEE.

[2]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

[3]  Xiang Zhang,et al.  Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems , 2015, ICLR.

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

[5]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[6]  Joelle Pineau,et al.  A Survey of Available Corpora for Building Data-Driven Dialogue Systems , 2015, Dialogue Discourse.

[7]  Rafael E. Banchs.  Movie-DiC: a Movie Dialogue Corpus for Research and Development , 2012, ACL.

[8]  Joelle Pineau,et al.  The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems , 2015, SIGDIAL Conference.

[9]  Yanjun Qi,et al.  Supervised semantic indexing , 2009, ECIR.

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

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

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

[13]  Rafael E. Banchs,et al.  The Fourth Dialog State Tracking Challenge , 2016, IWSDS.

[14]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[15]  Peter Stone,et al.  Cobot in LambdaMOO: A Social Statistics Agent , 2000, AAAI/IAAI.

[16]  Oliver Lemon,et al.  A Simple and Generic Belief Tracking Mechanism for the Dialog State Tracking Challenge: On the believability of observed information , 2013, SIGDIAL Conference.

[17]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[18]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[19]  David Vandyke,et al.  Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems , 2015, SIGDIAL Conference.

[20]  Matthew Henderson,et al.  Word-Based Dialog State Tracking with Recurrent Neural Networks , 2014, SIGDIAL Conference.

[21]  Peter Clark,et al.  Learning Knowledge Graphs for Question Answering through Conversational Dialog , 2015, NAACL.

[22]  Sina Jafarpour,et al.  Filter, Rank, and Transfer the Knowledge: Learning to Chat , 2010 .

[23]  Hao Wang,et al.  A Dataset for Research on Short-Text Conversations , 2013, EMNLP.

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

[25]  Dongho Kim,et al.  Incremental on-line adaptation of POMDP-based dialogue managers to extended domains , 2014, INTERSPEECH.

[26]  Alexander I. Rudnicky,et al.  Expanding the Scope of the ATIS Task: The ATIS-3 Corpus , 1994, HLT.

[27]  David Vandyke,et al.  Learning from real users: rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems , 2015, INTERSPEECH.

[28]  Joelle Pineau,et al.  On the Evaluation of Dialogue Systems with Next Utterance Classification , 2016, SIGDIAL Conference.

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

[30]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[31]  Gökhan Tür,et al.  End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding , 2016, INTERSPEECH.

[32]  Omer Levy,et al.  Published as a conference paper at ICLR 2018 S IMULATING A CTION D YNAMICS WITH N EURAL P ROCESS N ETWORKS , 2018 .

[33]  Helen F. Hastie,et al.  A survey on metrics for the evaluation of user simulations , 2012, The Knowledge Engineering Review.

[34]  Kallirroi Georgila,et al.  An ISU Dialogue System Exhibiting Reinforcement Learning of Dialogue Policies: Generic Slot-Filling in the TALK In-car System , 2006, EACL.