Using Dempster-Shafer Evidence Theory for Dialog State Tracking

In a task oriented spoken dialogue system, the automatic speech recognition (ASR) and spoken language understanding (SLU) modules usually provide multiple uncertain results, which may be related or divergent. Previously, researchers used classical probability theory based approach to solve this problem, but it is difficult to handle results combination and conflict. In this paper, we describe a novel target-based state tracking algorithm based on Dempster-Shafer(D-S) theory to deal with ASR and SLU uncertain issues. The n-best recognition results of different dialog turns are combined to update the current dialog state using evidence theory. Our method can be easily integrated into existing dialogue system. The effectiveness of our approach is demonstrated on a song-on-demand task, and performs better than traditional probability based methods.

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

[2]  Ji Wu,et al.  An entropy minimization framework for goal-driven dialogue management , 2015, INTERSPEECH.

[3]  Ji Wu,et al.  Target-Based State and Tracking Algorithm for Spoken Dialogue System , 2016, INTERSPEECH.

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

[5]  Jonathan Weisberg,et al.  Dempster-Shafer Theory , 2010 .

[6]  Xiaohui Zhang,et al.  Improving deep neural network acoustic models using generalized maxout networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[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]  Arthur P. Dempster,et al.  Upper and Lower Probabilities Induced by a Multivalued Mapping , 1967, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[9]  Kari Sentz,et al.  Combination of Evidence in Dempster-Shafer Theory , 2002 .

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

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

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

[13]  Christopher D. Manning,et al.  A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue , 2017, EACL.

[14]  Wayne H. Ward,et al.  Recent Improvements in the CMU Spoken Language Understanding System , 1994, HLT.

[15]  Chin-Hui Lee,et al.  A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management Through Dynamic Stochastic State Evolution , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[16]  Ji Wu,et al.  Subword scheme for keyword search , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[17]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[18]  Rafael E. Banchs,et al.  The fifth dialog state tracking challenge , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[19]  John E. Renaud,et al.  Uncertainty quantification using evidence theory in multidisciplinary design optimization , 2004, Reliab. Eng. Syst. Saf..

[20]  Z. Mourelatos,et al.  A Design Optimization Method Using Evidence Theory , 2006, DAC 2005.

[21]  Malcolm J. Beynon,et al.  The Dempster-Shafer Theory , 2009, Encyclopedia of Artificial Intelligence.

[22]  Qi Hu,et al.  An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking , 2018, ACL.

[23]  Alessandro Saffiotti,et al.  The Transferable Belief Model , 1991, ECSQARU.

[24]  Jianfeng Gao,et al.  Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access , 2016, ACL.