Mon, Oct 05, 2020 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
Ph.D. Defense - Eli Pincus 10/05 2:00 pm "An Investigation of Fully Interactive Multi-Role Dialogue Agents"
Ph.D. Candidate: Eli Pincus
Date: Monday, October 5, 2020
Time: 2:00 pm - 4:00 pm
Committee: David Traum (chair), Maja Mataric, Peter Kim
Title: An Investigation of Fully Interactive Multi-Role Dialogue Agents
In the course of their lives human perform multiple roles such as work and social roles. However, current research in human-computer dialogue has focused on dialogue agents that perform only one role of an interaction. For example, Apple's Siri acts mainly as an assistant. In this thesis we helps fill the gap in multi-role dialogue agent research.
We describe an architecture that endows a test-bed agent with core dialogue management capabilities for both roles of a word-guessing game but can be adapted for different embodiments including virtual human, robot, and a non-embodied web-platform that enables use of the test-bed agent in "in the wild" experiments. We incrementally evaluate design decisions for the test-bed agent that decrease the chance that our later experiments, that more directly evaluate the agent's multi-role capabilities, failed to find effects due to confounds stemming from poor design decisions. We establish that multi-role agents, when compared to single-role versions of the same agent, are able to elicit enjoyment from users without negatively impacting user's perceptions. We also use an "in the wild" experiment to prove that a multi-role content sourcing strategy can be superior to other scalable content sourcing strategies.
Join Zoom Meeting
Meeting ID: 927 9149 9440
Audiences: Everyone Is Invited
Contact: Lizsl De Leon