A tractable DDN-POMDP Approach to Affective Dialogue Modeling for General Probabilistic Frame-based Dialogue Systems

We propose a new approach to developing a tractable affective dialogue model for general probabilistic frame-based dialogue systems. The dialogue model, based on the Partially Observable Markov Decision Process (POMDP) and the Dynamic Decision Network (DDN) techniques, is composed of two main parts, the slot level dialogue manager and the global dialogue manager. Our implemented dialogue manager prototype can handle hundreds of slots; each slot might have many values. A first evaluation of the slot level dialogue manager (1-slot case) showed that with a 95% confidence level the DDN-POMDP dialogue strategy outperforms three simple handcrafted dialogue strategies when the user's action error is induced by stress.

[1]  M. Tulder.  Chapter 1 , 2006, European Spine Journal.

[2]  Kindler-Rohrborn,et al.  In press , 1994, Molecular carcinogenesis.

[3]  Harry Bunt,et al.  Context and Dialogue Control , 1994 .

[4]  Eric Horvitz,et al.  Conversation as Action Under Uncertainty , 2000, UAI.

[5]  Elisabeth André,et al.  Proceedings of the 8th international conference on Intelligent user interfaces , 2002 .

[6]  Thomas L. Dean,et al.  A Model for Projection and Action , 1989, IJCAI.

[7]  J. Meigs,et al.  WHO Technical Report , 1954, The Yale Journal of Biology and Medicine.

[8]  G. Miller,et al.  Cognitive science. , 1981, Science.

[9]  Pascal Poupart,et al.  Factored partially observable Markov decision processes for dialogue management , 2005 .

[10]  Eugene Ball.  A Bayesian Heart: Computer Recognition and Simulation of Emotion , 2006 .

[11]  Roberto Pieraccini,et al.  User modeling for spoken dialogue system evaluation , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

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

[13]  Anton Nijholt,et al.  Toward Affective Dialogue Modeling using Partially Observable Markov Decision Processes , 2006 .

[14]  Martin Rajman,et al.  Rapid Dialogue Prototyping Methodology , 2004, TSD.

[15]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[16]  Leslie Pack Kaelbling,et al.  Acting Optimally in Partially Observable Stochastic Domains , 1994, AAAI.

[17]  Steve Young,et al.  Scaling POMDPs for dialog management with composite summary point-based value iteration (CSPBVI) , 2006 .

[18]  James F. Allen,et al.  Towards Conversational Human-Computer Interaction , 2000 .

[19]  Herbert H. Clark,et al.  Contributing to Discourse , 1989, Cogn. Sci..

[20]  Louise Poissant.  Part I , 1996, Leonardo.

[21]  Craig Boutilier,et al.  Computing Optimal Policies for Partially Observable Decision Processes Using Compact Representations , 1996, AAAI/IAAI, Vol. 2.

[22]  James F. Allen,et al.  Toward Conversational Human-Computer Interaction , 2001, AI Mag..

[23]  E. Schegloff,et al.  A simplest systematics for the organization of turn-taking for conversation , 1974 .

[24]  Joelle Pineau,et al.  Spoken Dialogue Management Using Probabilistic Reasoning , 2000, ACL.

[25]  Simon King,et al.  IEEE Workshop on automatic speech recognition and understanding , 2009 .

[26]  Nikos A. Vlassis,et al.  Perseus: Randomized Point-based Value Iteration for POMDPs , 2005, J. Artif. Intell. Res..

[27]  R. Lathe.  Phd by thesis , 1988, Nature.

[28]  Baining Guo,et al.  Spoken dialogue management as planning and acting under uncertainty , 2001, INTERSPEECH.

[29]  Qiang Ji,et al.  Active affective State detection and user assistance with dynamic bayesian networks , 2005, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[30]  Nicole Novielli,et al.  User modeling and adaptation in health promotion dialogs with an animated character , 2006, J. Biomed. Informatics.

[31]  Amos Storkey.  UAI '00: Proceedings of the 16th Conference in Uncertainty in Artificial Intelligence , 2000 .

[32]  Cristina Conati,et al.  Inferring user goals from personality and behavior in a causal model of user affect , 2003, IUI '03.

[33]  Olivier Pietquin,et al.  A Framework for Unsupervised Learning of Dialogue Strategies , 2004 .

[34]  Hui Ye,et al.  The Hidden Information State Approach to Dialog Management , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[35]  Joelle Pineau,et al.  A Hierarchical Approach to POMDP Planning and Execution , 2004 .