Dynamic Bayesian Networks for NLU Simulation with Application to Dialog Optimal Strategy Learning

Abstract : In this paper, we propose to add a model for NLU-related error generation in a modular environment for computer-based simulation of man-machine spoken dialogs. This model is jointly designed with a user model. Both of them are based on the same underlying Bayesian Network used with different parameters in such a way that it can generate a consistent user behavior, according to a goal and the interaction history, and been used as a concept classifier. The proposed simulation environment was used to train a reinforcement-learning algorithm on a simple form-filling task and the results of this experiment show that the addition of the NLU model helps pointing out problematic situations that may occur because of misunderstandings and modifying the dialog strategy accordingly.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), Jul 2006, Toulouse, France. I, pp.49-52, 2006
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal-supelec.archives-ouvertes.fr/hal-00216013
Contributeur : Sébastien Van Luchene <>
Soumis le : mardi 12 février 2008 - 15:13:40
Dernière modification le : mardi 12 février 2019 - 14:28:55
Document(s) archivé(s) le : jeudi 15 avril 2010 - 16:07:15

Fichier

Supelec16.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00216013, version 1

Collections

Citation

Olivier Pietquin, Thierry Dutoit. Dynamic Bayesian Networks for NLU Simulation with Application to Dialog Optimal Strategy Learning. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), Jul 2006, Toulouse, France. I, pp.49-52, 2006. 〈hal-00216013〉

Partager

Métriques

Consultations de la notice

162

Téléchargements de fichiers

93