Knowledge-based Dialog State Tracking

This paper presents two discriminative knowledge-based dialog state trackers and their results on the Dialog State Tracking Challenge (DSTC) 2 and 3 datasets. The first tracker was submitted to the DSTC3 competition and scored second in the joint accuracy. The second tracker developed after the DSTC3 submission deadline gives even better results on the DSTC2 and DSTC3 datasets. It performs on par with the state of the art machine learning-based trackers while offering better interpretability. We summarize recent directions in the dialog state tracking (DST) and also discuss possible decomposition of the DST problem. Based on the results of DSTC2 and DSTC3 we analyze suitability of different techniques for each of the DST subproblems. Results of the trackers highlight the importance of Spoken Language Understanding (SLU) for the last two DSTCs.

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

[2]  Kee-Eung Kim,et al.  Optimizing Generative Dialog State Tracker via Cascading Gradient Descent , 2014, SIGDIAL Conference.

[3]  Jason D. Williams.  Challenges and Opportunities for State Tracking in Statistical Spoken Dialog Systems: Results From Two Public Deployments , 2012, IEEE Journal of Selected Topics in Signal Processing.

[4]  Yonghong Yan,et al.  Markovian Discriminative Modeling for Dialog State Tracking , 2014, SIGDIAL Conference.

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

[6]  Sungjin Lee.  Extrinsic Evaluation of Dialog State Tracking and Predictive Metrics for Dialog Policy Optimization , 2014, SIGDIAL Conference.

[7]  Kee-Eung Kim,et al.  Engineering Statistical Dialog State Trackers: A Case Study on DSTC , 2013, SIGDIAL Conference.

[8]  Lu Chen,et al.  The SJTU System for Dialog State Tracking Challenge 2 , 2014, SIGDIAL Conference.

[9]  Jason D. Williams.  A critical analysis of two statistical spoken dialog systems in public use , 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

[10]  Ronnie W. Smith.  Comparative Error Analysis of Dialog State Tracking , 2014, SIGDIAL Conference.

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

[12]  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.

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

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

[15]  Jason D. Williams.  Incremental partition recombination for efficient tracking of multiple dialog states , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

[17]  Angeliki Metallinou,et al.  Discriminative state tracking for spoken dialog systems , 2013, ACL.

[18]  Matthew Henderson,et al.  Discriminative spoken language understanding using word confusion networks , 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

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

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

[21]  Alexander I. Rudnicky,et al.  A “K Hypotheses + Other” Belief Updating Model , 2006 .

[22]  Rudolf Kadlec,et al.  IBM's Belief Tracker: Results On Dialog State Tracking Challenge Datasets , 2014, DM@EACL.

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

[24]  Steve J. Young,et al.  Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems , 2010, Comput. Speech Lang..

[25]  Matthew Henderson,et al.  Deep Neural Network Approach for the Dialog State Tracking Challenge , 2013, SIGDIAL Conference.