Action State Update Approach to Dialogue Management

Utterance interpretation is one of the main functions of a dialogue manager, which is the key component of a dialogue system. We propose the action state update approach (ASU) for utterance interpretation, featuring a statistically trained binary classifier used to detect dialogue state update actions in the text of a user utterance. Our goal is to interpret referring expressions in user input without a domain-specific natural language understanding component. For training the model, we use active learning to automatically select simulated training examples. With both user-simulated and interactive human evaluations, we show that the ASU approach successfully interprets user utterances in a dialogue system, including those with referring expressions.

[1]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[2]  Hannes Schulz,et al.  Frames: a corpus for adding memory to goal-oriented dialogue systems , 2017, SIGDIAL Conference.

[3]  Dilek Z. Hakkani-Tür,et al.  End-to-end joint learning of natural language understanding and dialogue manager , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Dilek Z. Hakkani-Tür,et al.  DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue , 2020, ArXiv.

[5]  Pierre Lison,et al.  Rapid Prototyping of Form-driven Dialogue Systems Using an Open-source Framework , 2016, SIGDIAL Conference.

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

[7]  Tsung-Hsien Wen,et al.  Neural Belief Tracker: Data-Driven Dialogue State Tracking , 2016, ACL.

[8]  Geoffrey Zweig,et al.  Fast and easy language understanding for dialog systems with Microsoft Language Understanding Intelligent Service (LUIS) , 2015, SIGDIAL Conference.

[9]  Srinivas Bangalore,et al.  Interaction between dialog structure and coreference resolution , 2010, 2010 IEEE Spoken Language Technology Workshop.

[10]  Michael Johnston,et al.  Knowledge-Graph Driven Information State Approach to Dialog , 2018, AAAI Workshops.

[11]  David Traum,et al.  The Information State Approach to Dialogue Management , 2003 .

[12]  Dilek Z. Hakkani-Tür,et al.  Multi-task Learning for Joint Language Understanding and Dialogue State Tracking , 2018, SIGDIAL Conference.

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

[14]  Yannick Versley,et al.  Anaphora Resolution: Algorithms, Resources, and Applications , 2016 .

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

[16]  Christopher Potts,et al.  Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding , 2017, TACL.

[17]  Raghav Gupta,et al.  Schema-Guided Dialogue State Tracking Task at DSTC8 , 2020, ArXiv.

[18]  Jason Williams.  A belief tracking challenge task for spoken dialog systems , 2012, SDCTD@NAACL-HLT.

[19]  Hui Ye,et al.  Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System , 2007, NAACL.

[20]  Anne H. Anderson,et al.  The Hcrc Map Task Corpus , 1991 .

[21]  Milica Gasic,et al.  The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management , 2010, Comput. Speech Lang..

[22]  Stefan Ultes,et al.  MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling , 2018, EMNLP.

[23]  Michael Johnston,et al.  Corpus and Annotation Towards NLU for Customer Ordering Dialogs , 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).