Task Lineages: Dialog State Tracking for Flexible Interaction

We consider the gap between user demands for seamless handling of complex interactions, and recent advances in dialog state tracking technologies. We propose a new statistical approach, Task Lineage-based Dialog State Tracking (TL-DST), aimed at seamlessly orchestrating multiple tasks with complex goals across multiple domains in continuous interaction. TL-DST consists of three components: (1) task frame parsing, (2) context fetching and (3) task state update (for which TL-DST takes advantage of previous work in dialog state tracking). There is at present very little publicly available multi-task, complex goal dialog data; however, as a proof of concept, we applied TL-DST to the Dialog State Tracking Challenge (DSTC) 2 data, resulting in state-of-the-art performance. TLDST also outperforms the DSTC baseline tracker on a set of pseudo-real datasets involving multiple tasks with complex goals which were synthesized using DSTC3 data.

[1]  Miroslav Vodolán,et al.  Hybrid Dialog State Tracker , 2015, ArXiv.

[2]  Steve J. Young,et al.  A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies , 2006, The Knowledge Engineering Review.

[3]  Sungjin Lee,et al.  Structured Discriminative Model For Dialog State Tracking , 2013, SIGDIAL Conference.

[4]  Samy Bengio,et al.  Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks , 2015, NIPS.

[5]  David Vandyke,et al.  Policy committee for adaptation in multi-domain spoken dialogue systems , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[6]  Antoine Raux,et al.  The Dialog State Tracking Challenge , 2013, SIGDIAL Conference.

[7]  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.

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

[9]  Thierry Dutoit,et al.  A probabilistic framework for dialog simulation and optimal strategy learning , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[10]  Jason D. Williams,et al.  Web-style ranking and SLU combination for dialog state tracking , 2014, SIGDIAL Conference.

[11]  Staffan Larsson,et al.  Information state and dialogue management in the TRINDI dialogue move engine toolkit , 2000, Natural Language Engineering.

[12]  Hiroshi G. Okuno,et al.  A Two-Stage Domain Selection Framework for Extensible Multi-Domain Spoken Dialogue Systems , 2011, SIGDIAL Conference.

[13]  Miroslav Vodolán,et al.  Knowledge-based Dialog State Tracking , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[14]  Oliver Lemon,et al.  Representing Uncertainty about Complex User Goals in Statistical Dialogue Systems , 2010, SIGDIAL Conference.

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

[16]  Maxine Eskénazi,et al.  An Unsupervised Approach to User Simulation: Toward Self-Improving Dialog Systems , 2012, SIGDIAL Conference.

[17]  Matthew Henderson,et al.  The third Dialog State Tracking Challenge , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[18]  Milica Gasic,et al.  Parameter learning for POMDP spoken dialogue models , 2010, 2010 IEEE Spoken Language Technology Workshop.

[19]  Gökhan Tür,et al.  A Discriminative Classification-Based Approach to Information State Updates for a Multi-Domain Dialog System , 2012, INTERSPEECH.

[20]  Lu Chen,et al.  Semantic parser enhancement for dialogue domain extension with little data , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[21]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[22]  C. Sidner,et al.  Plans for Discourse , 1988 .

[23]  Adwait Ratnaparkhi,et al.  Belief Tracking with Stacked Relational Trees , 2015, SIGDIAL Conference.

[24]  Filip Jurcícek,et al.  Comparison of Bayesian Discriminative and Generative Models for Dialogue State Tracking , 2013, SIGDIAL Conference.

[25]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[26]  Hao Tian,et al.  Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System , 2014, EMNLP.

[27]  Antoine Raux,et al.  The Dialog State Tracking Challenge Series: A Review , 2016, Dialogue Discourse.

[28]  Karen E. Lochbaum,et al.  A Collaborative Planning Model of Intentional Structure , 1998, CL.

[29]  Lu Chen,et al.  A generalized rule based tracker for dialogue state tracking , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[30]  Maxine Eskénazi,et al.  Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description , 2013, SIGDIAL Conference.

[31]  Young-Bum Kim,et al.  Task Completion Platform: A self-serve multi-domain goal oriented dialogue platform , 2016, NAACL.

[32]  Philip R. Cohen,et al.  Plans for Discourse , 2003 .