A Conventional Dialogue Model based on Empirically Specified Dialogue Games

Guillaume Dubuisson Duplessis 1 Alexandre Pauchet 1 Nathalie Chaignaud 1 J.-Ph Kotowicz 1
1 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
Abstract : Our work aims at designing a dialogue manager dedicated to agents that interact with humans. In this article, we show how empirically specified dialogue games can be employed on both interpretative and generative levels of dialogue management. We present DOGMA, an open-source module that can be used by an agent to manage its conventional communicative behaviour. We show that our library of dialogue games can be used into DOGMA to generate fragments of dialogue that are strongly coherent from a human perspective.
Keywords : Human-Machine Interaction Dialogue Management Dialogue Games
Type de document :
Communication dans un congrès
IEEE 27th International Conference on Tools with Artificial Intelligence, Nov 2015, Vietri sul Mare, Italy. 2015 IEEE 27th International Conference on Tools with Artificial Intelligence, pp.997-1004, 2015, 〈10.1109/ICTAI.2015.143〉
Liste complète des métadonnées

Littérature citée [29 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01228571
Contributeur : Guillaume Dubuisson Duplessis <>
Soumis le : vendredi 13 novembre 2015 - 13:03:07
Dernière modification le : samedi 27 octobre 2018 - 01:22:25
Document(s) archivé(s) le : vendredi 28 avril 2017 - 21:48:04

Fichier

ICTAI2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

LITIS | COMUE-NORMANDIE | INSA-ROUEN | UNIROUEN

Citation

Guillaume Dubuisson Duplessis, Alexandre Pauchet, Nathalie Chaignaud, J.-Ph Kotowicz. A Conventional Dialogue Model based on Empirically Specified Dialogue Games. IEEE 27th International Conference on Tools with Artificial Intelligence, Nov 2015, Vietri sul Mare, Italy. 2015 IEEE 27th International Conference on Tools with Artificial Intelligence, pp.997-1004, 2015, 〈10.1109/ICTAI.2015.143〉. 〈hal-01228571〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

172

Téléchargements de fichiers

195

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD