Authors:
Nikita Mattar
and
Ipke Wachsmuth
Affiliation:
Bielefeld University, Germany
Keyword(s):
Conversation topics, Embodied conversational agents, Human-agent interaction, Long-term interactions, Person memory, Small talk, Social categories, Stereotypes.
Related
Ontology
Subjects/Areas/Topics:
Agent Models and Architectures
;
Agents
;
Artificial Intelligence
;
Cognitive Systems
;
Computational Intelligence
;
Conversational Agents
;
Evolutionary Computing
;
Knowledge Representation and Reasoning
;
Reactive AI
;
Soft Computing
;
Symbolic Systems
Abstract:
Humans make extensive use of specialized representations to remember people they interacted with. While current research on embodied conversational agents focuses on the relationship between agent and interlocutor, the representation of the latter is mostly neglected. But information about others are inevitable for an agent to adapt to its interlocutors and to establish long-term relationships with them. In this work, we present a model of Person Memory for virtual agents. We discuss what kinds of information have to be stored about people. Furthermore, we stress the importance of social categories. In our scenario, we focus on first encounters between our agent and people. We show how the agent is able to exploit his Person Memory to acquire information about others during Small Talk and guide the conversation.