Exploiting Machine-Transcribed Dialog Corpus to Improve Multiple Dialog States Tracking Methods

This paper proposes the use of unsupervised approaches to improve components of partition-based belief tracking systems. The proposed method adopts a dynamic Bayesian network to learn the user action model directly from a machine-transcribed dialog corpus. It also addresses confidence score calibration to improve the observation model in a unsupervised manner using dialog-level grounding information. To verify the effectiveness of the proposed method, we applied it to the Let's Go domain (Raux et al., 2005). Overall system performance for several comparative models were measured. The results show that the proposed method can learn an effective user action model without human intervention. In addition, the calibrated confidence score was verified by demonstrating the positive influence on the user action model learning process and on overall system performance.

[1]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

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

[3]  Milica Gasic,et al.  Effective handling of dialogue state in the hidden information state POMDP-based dialogue manager , 2011, TSLP.

[4]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

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

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

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

[8]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[9]  Kallirroi Georgila,et al.  Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets , 2008, CL.

[10]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[11]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

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

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

[14]  Jason Williams,et al.  Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System , 2008, ACL.

[15]  Jason D. Williams.  Exploiting the ASR n-best by tracking multiple dialog state hypotheses , 2008, INTERSPEECH.

[16]  Yi Ma,et al.  Efficient Probabilistic Tracking of User Goal and Dialog History for Spoken Dialog Systems , 2011, INTERSPEECH.

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

[18]  G. Parisi,et al.  Statistical Field Theory , 1988 .

[19]  Milica Gasic,et al.  Modelling user behaviour in the HIS-POMDP dialogue manager , 2008, 2008 IEEE Spoken Language Technology Workshop.

[20]  Steve J. Young,et al.  Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs , 2011, TSLP.

[21]  Maxine Eskénazi,et al.  Let's go public! taking a spoken dialog system to the real world , 2005, INTERSPEECH.