Skip to Main content Skip to Navigation
Theses

Modèle de comportement communicatif conventionnel pour un agent en interaction avec des humains : approche par jeux de dialogue

Abstract : This research work aims at improving the communicative behaviour of software agents interacting with humans. To this purpose, we present a data-driven methodology based on the study of a task-oriented corpus consisting of Human-Human interactions. This corpus is processed in two main steps: its enrishment through an annotation phase and a regularity extraction phase. Our research work focuses on interaction patterns, that is to say regularities observed at the level of dialogical interaction. We study high-level structures that can be specified from these patterns. These structures form the basis of the interaction model for an agent that can be integrated into a deliberative process. We present a framework to specify dialogue games from these patterns based on the notion of social commitments and conversational gameboard. This framework is independent of the private states of interacting agents. We exemplify the specification of dialogue games by implementing all the steps of our methodology on a task-oriented corpus. The produced games are validated by showing that they appropriately describe the patterns appearing in a reference corpus. Eventually, we show that an agent can take advantage of our model to regulate its conventional communicative behaviour on both interpretative and generative levels. We implement this model into Dogma, a module that can be used by an agent to manage its communicative behaviour in a two-interlocutor dialogue.
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-01017542
Contributor : Guillaume Dubuisson Duplessis <>
Submitted on : Wednesday, July 2, 2014 - 4:37:50 PM
Last modification on : Tuesday, February 5, 2019 - 11:44:23 AM
Long-term archiving on: : Thursday, October 2, 2014 - 11:47:08 AM

Identifiers

  • HAL Id : tel-01017542, version 1

Citation

Guillaume Dubuisson Duplessis. Modèle de comportement communicatif conventionnel pour un agent en interaction avec des humains : approche par jeux de dialogue. Intelligence artificielle [cs.AI]. INSA de Rouen, 2014. Français. ⟨tel-01017542v1⟩

Share

Metrics

Record views

203

Files downloads

861