Modelling strategic conversation: model, annotation design and corpus (poster)
Résumé
A Gricean view of cognitive agents holds that agents are fully rational and adhere to the maxims of conversation that entail that speakers adopt shared intentions and fully aligned preferences–e.g. (Allen and Litman, 1987; Lochbaum, 1998). These assumptions are unwarranted in many conversational settings. In this paper we propose a different view and an annotation scheme for it.
Domaines
Intelligence artificielle [cs.AI]
Origine : Fichiers produits par l'(les) auteur(s)