This is a past event
Title: Informing Dialogue Strategy through Argumentation-Derived Evidence
Abstract: An important and non-trivial factor for effectively developing and resourcing plans in a collaborative context is an understanding of the policy and resource availability constraints under which others operate. Can agents exploit evidence derived from past dialogues to improve the outcome of collaborative problem solving?What argument(s) should be put forward in order to persuade another agent to do something? How effective were similar arguments in convincing similar agents in similar circumstances? What are the risks associated with putting certain arguments forward? These are important questions for an autonomous agent collaborating with others to solve a problem. In this work, we present a decision-making mechanism where models of other agents are refined through evidence derived from argumentation-based dialogues, and where these models are used to guide future argumentation strategy. We combine argumentation, machine learning and decision theory in a novel way that enables agents to autonomously reason about the constraints (e.g., policies) that others are operating within, and make informed decisions about whom to delegate a task to. We demonstrate the utility of this novel combination of techniques through empirical evaluation in a plan resourcing domain. Our evaluation shows that a combination of decision-theoretic and machine learning techniques can significantly help to improve dialogical outcomes.
- Speaker
- David Emele, University of Aberdeen
- Venue
- Meston 203