论文信息 - Dialog State Tracking using Conditional Random Fields

Dialog State Tracking using Conditional Random Fields

This paper presents our approach to dialog state tracking for the Dialog State Tracking Challenge task. In our approach we use discriminative general structured conditional random fields, instead of traditional generative directed graphic models, to incorporate arbitrary overlapping features. Our approach outperforms the simple 1-best tracking approach.

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

[2] Andrew McCallum,et al. An Introduction to Conditional Random Fields , 2010, Found. Trends Mach. Learn..

[3] Antoine Raux,et al. Dialog State Tracking Challenge Handbook , 2012 .

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

[5] 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.

[6] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

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

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

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

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

[11] Y. Weiss,et al. Finding the M Most Probable Configurations using Loopy Belief Propagation , 2003, NIPS 2003.