In this talk I will describe the use of theories of agent
collaboration and human dialogue processing in providing a principled
basis for the design of web interfaces to multimedia information
stores. I will discuss a system called DIAL to illustrate the
efficacy of this approach. DIAL builds a representation of context
that is based on the collaborative plans of the system and its
user and uses this contextual information to reduce the communication
burden.
Context is represented by a structure of intentions that a
user is pursuing. This structure is modified as tasks are completed
or task descriptions are refined. DIAL interprets information
requests relative to the prevailing context as it is represented
by this structure. As a result, requests can be expressed more
economically; contextual information is added by the system.
Furthermore, DIAL uses information about the intentional context
to respond and act collaboratively, rather than in the master-slave
style typical of most current human-computer interfaces. DIAL
and the access method it supports provide a unique support tool
for distance learning environments as well as a demonstration
of a general way in which agent models can be used to improve
human-computer communication.
This is joint work with Barbara Grosz of Harvard University.
Charlie Ortiz
is a Senior Computer Scientist in the AI
Center at SRI. His research interests include: Commonsense
reasoning: action, causation, and counterfactuals; Collaborative
planning and rational agent architectures; Planning under incomplete
information; Applications of logic to commonsense reasoning;
Logic programming; Collaborative user interfaces, large-scale
information management, and distance learning. He received his
PhD from the Department of Computer and Information Science,
University of Pennsylvania and was a postdoctoral fellow, at
Harvard University.