Human-Machine Dialogue as a Stochastic Game

Abstract : In this paper, an original framework to model human-machine spoken dialogues is proposed to deal with co-adaptation between users and Spoken Dialogue Systems in non-cooperative tasks. The conversation is modeled as a Stochastic Game: both the user and the system have their own preferences but have to come up with an agreement to solve a non-cooperative task. They are jointly trained so the Dialogue Manager learns the optimal strategy against the best possible user. Results obtained by simulation show that non-trivial strategies are learned and that this framework is suitable for dialogue modeling.
Type de document :
Communication dans un congrès
16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL 2015), Sep 2015, Prague, Czech Republic. 2015, 〈http://www.sigdial.org/workshops/conference16/〉
Liste complète des métadonnées

Littérature citée [42 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01225848
Contributeur : Olivier Pietquin <>
Soumis le : vendredi 6 novembre 2015 - 18:35:03
Dernière modification le : vendredi 13 avril 2018 - 01:26:59
Document(s) archivé(s) le : lundi 8 février 2016 - 13:02:27

Fichier

W15-4602.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01225848, version 1

Collections

Citation

Merwan Barlier, Julien Perolat, Romain Laroche, Olivier Pietquin. Human-Machine Dialogue as a Stochastic Game. 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL 2015), Sep 2015, Prague, Czech Republic. 2015, 〈http://www.sigdial.org/workshops/conference16/〉. 〈hal-01225848〉

Partager

Métriques

Consultations de la notice

265

Téléchargements de fichiers

252