A Conventional Dialogue Model Based on Dialogue Patterns

Guillaume Dubuisson Duplessis (1) , Alexandre Pauchet (2, 3) , Nathalie Chaignaud (2, 3) , Jean-Philippe Kotowicz (2, 3)

1 ISIR - Institut des Systèmes Intelligents et de Robotique
2 MIND - LITIS - Equipe Multi-agent, Interaction, Décision
3 INSA Rouen Normandie - Institut national des sciences appliquées Rouen Normandie

Our work aims at designing a dialogue manager dedicated to agents that interact with humans. In this article, we investigate how dialogue patterns at the dialogue act level extracted from Human-Human interactions can be fruitfully used by a software agent to interact with a human. We show how these patterns can be leveraged via a dialogue game structure in order to benefit to the dialogue management process of an agent. We describe 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.

Domaines: Interface homme-machine [cs.HC]

Guillaume Dubuisson Duplessis, Alexandre Pauchet, Nathalie Chaignaud, Jean-Philippe Kotowicz. A Conventional Dialogue Model Based on Dialogue Patterns. International Journal on Artificial Intelligence Tools, 2017, 26 (01), pp.1760009. ⟨10.1142/S0218213017600090⟩. ⟨hal-02121702⟩