Authors:
Lorraine Vanel
1
;
2
;
Alya Yacoubi
2
and
Chloé Clavel
1
Affiliations:
1
LTCI, Telecom-Paris, Institut Polytechnique de Paris, France
;
2
Zaion, Paris, France
Keyword(s):
Task-Oriented Dialogue Systems, Social Dialogue, Emotional Dialogue, Persona, Empathetic Conversational System, Conversational Dataset, Neural Generation Models, End-to-End Generation.
Abstract:
As dialogue systems are expected to display more and more “human” features, a subfield of conversational artificial intelligence (AI) has emerged, aiming to make virtual agents socially competent. As the common outlook firmly places emotion in the domain of chit-chatting, most of the studies tackle the problem of social behaviour in open domain applications. In this paper, we provide an overview of such approaches and think about how they can be applied to a task-oriented setting. The angle we explore is the influence of data on socio-emotional neural generation models. We focus on three aspects: dialogue strategies, emotional strategies and persona.