Using an Activity Model to Address Issues in Task-Oriented Dialogue Interaction over Extended Periods

Alexander Gruenstein and Lawrence Cavedon

Collaborative natural dialogue offers a powerful medium for interaction between humans and intelligent autonomous agents, particularly for complex systems operating in dynamic, real-time environments, containing multiple concurrent activities. Dealing with dialogue interaction over an extended period raises specific needs, such as: mixed initiative; task-status reporting; explanation; providing grounding context; and handling multiple open topics. We describe the use of an Activity Model as the basis for implementing such capabilities.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.