Giving instructions in virtual environments by corpus based selection

Luciana Benotti 1 Alexandre Denis 2
1 Equipe d'Informatique Linguistique - Grupo de Procesamiento de Lenguaje Natural (PLN)
LIGM - Laboratoire d'Informatique Gaspard-Monge, FaMAF - Facultad de Matemática, Astronomía y Física [Cordoba]
2 TALARIS - Natural Language Processing: representation, inference and semantics
Inria Nancy - Grand Est, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Instruction giving can be used in several applications, ranging from trainers in simulated worlds to non player characters for virtual games. In this paper we present a novel algorithm for rapidly prototyping virtual instruction-giving agents from human-human corpora without manual annotation. Automatically prototyping full-fledged dialogue systems from corpora is far from being a reality nowadays. Our approach is restricted in that only the virtual instructor can perform speech acts while the user responses are limited to physical actions in the virtual worlds. We have defined an algorithm that, given a task-based corpus situated in a virtual world, which contains human instructor's speech acts and the user's responses as physical actions, generates a virtual instructor that robustly helps a user achieve a given task in the virtual world. We explain how this algorithm can be used for generating a virtual instructor for a game-like, task-oriented virtual world. We evaluate the virtual instructor with human users using task-oriented as well as user satisfaction metrics. We compare our results with both human and rule-based virtual instructors hand-coded for the same task.
Type de document :
Communication dans un congrès
SIGdial Meeting on Discourse and Dialogue, Jun 2011, Portland, United States. 2011
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00636303
Contributeur : Alexandre Denis <>
Soumis le : jeudi 27 octobre 2011 - 11:27:04
Dernière modification le : mercredi 11 avril 2018 - 12:12:04
Document(s) archivé(s) le : jeudi 15 novembre 2012 - 10:40:26

Fichier

sigdial2011.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00636303, version 1

Citation

Luciana Benotti, Alexandre Denis. Giving instructions in virtual environments by corpus based selection. SIGdial Meeting on Discourse and Dialogue, Jun 2011, Portland, United States. 2011. 〈inria-00636303〉

Partager

Métriques

Consultations de la notice

220

Téléchargements de fichiers

149