Prototyping virtual instructors from human-human corpora

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 : Virtual instructors 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 instructors from human-human corpora without manual annotation. Automatically prototyping full-fledged dialogue systems from corpora is far from being a reality nowadays. Our algorithm is restricted in that only the virtual instructor can perform speech acts while the user responses are limited to physical actions in the virtual world. We evaluate a virtual instructor, generated using this algorithm, with human users. We compare our results both with human instructors and rule-based virtual instructors hand-coded for the same task.
Type de document :
Communication dans un congrès
Association for Computational Linguistics: Human Language Technologies, Jun 2011, Portland, United States. 2011
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00636300
Contributeur : Alexandre Denis <>
Soumis le : jeudi 27 octobre 2011 - 11:20:25
Dernière modification le : mercredi 11 avril 2018 - 12:12:04
Document(s) archivé(s) le : jeudi 15 novembre 2012 - 10:40:20

Fichier

acl-benotti-denis-2011.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00636300, version 1

Citation

Luciana Benotti, Alexandre Denis. Prototyping virtual instructors from human-human corpora. Association for Computational Linguistics: Human Language Technologies, Jun 2011, Portland, United States. 2011. 〈inria-00636300〉

Partager

Métriques

Consultations de la notice

142

Téléchargements de fichiers

201