SEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection

Dialogue response selection is an important part of Task-oriented Dialogue Systems (TDSs); it aims to predict an appropriate response given a dialogue context. Obtaining key information from a complex, long dialogue context is challenging, especially when different sources of information are available, e.g., the user's utterances, the system's responses, and results retrieved from a knowledge base (KB). Previous work ignores the type of information source and merges sources for response selection. However, accounting for the source type may lead to remarkable differences in the quality of response selection. We propose the Source-aware Recurrent Entity Network (SEntNet), which is aware of different information sources for the response selection process. SEntNet achieves this by employing source-specific memories to exploit differences in the usage of words and syntactic structure from different information sources (user, system, and KB). Experimental results show that SEntNet obtains 91.0% accuracy on the Dialog bAbI dataset, outperforming prior work by 4.7%. On the DSTC2 dataset, SEntNet obtains an accuracy of 41.2%, beating source unaware recurrent entity networks by 2.4%.

[1]  Jiliang Tang,et al.  A Survey on Dialogue Systems: Recent Advances and New Frontiers , 2017, SKDD.

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

[3]  Pascale Fung,et al.  End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-Oriented Dialog , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Geoffrey Zweig,et al.  Attention with Intention for a Neural Network Conversation Model , 2015, ArXiv.

[5]  Maxine Eskénazi,et al.  Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning , 2016, SIGDIAL Conference.

[6]  Kevin Gimpel,et al.  Towards Universal Paraphrastic Sentence Embeddings , 2015, ICLR.

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

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

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

[10]  Geoffrey Zweig,et al.  Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning , 2017, ACL.

[11]  Ta-Chung Chi,et al.  Dynamic time-aware attention to speaker roles and contexts for spoken language understanding , 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

[12]  Julien Perez,et al.  Gated End-to-End Memory Networks , 2016, EACL.

[13]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[14]  Takashi Ushio,et al.  End-to-end memory networks with word abstraction and contextual numbering for goal-oriented tasks , 2017 .

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

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

[17]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[18]  Pascale Fung,et al.  End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning , 2017 .

[19]  Jianfeng Gao,et al.  Dialog System Technology Challenge 7 , 2019, ArXiv.

[20]  Jason Weston,et al.  Tracking the World State with Recurrent Entity Networks , 2016, ICLR.

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

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

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

[24]  Meng Yang,et al.  Hierarchical Hybrid Code Networks for Task-Oriented Dialogue , 2018, ICIC.

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

[26]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

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

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

[29]  Jeong-Won Cha,et al.  End-to-end task dependent recurrent entity network for goal-oriented dialog learning , 2019, Comput. Speech Lang..

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