12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Efficient Probabilistic Tracking of User Goal and Dialog History for Spoken Dialog Systems

Antoine Raux (1), Yi Ma (2)

(1) Honda Research Institute USA, USA
(2) Ohio State University, USA

In this paper, we describe Dynamic Probabilistic Ontology Trees, a new probabilistic model to track dialog state in a dialog system. Our model captures both the user goal and the history of user dialog acts using a unified Bayesian Network. We perform efficient inference using a form of blocked Gibbs sampling designed to exploit the structure of the model. Evaluation on a corpus of dialogs from the CMU Let's Go system shows that our approach significantly outperforms a deterministic baseline, exploiting long N-best lists without loss of accuracy.

Full Paper

Bibliographic reference.  Raux, Antoine / Ma, Yi (2011): "Efficient probabilistic tracking of user goal and dialog history for spoken dialog systems", In INTERSPEECH-2011, 801-804.