Computer Science and Engineering Department
University of Wisconsin - Parkside
2. Speech and Natural Language Understanding.
The research issue that I am addressing is how to represent and reason about interactive discourse to determine when an artificial agent should take control of a given interaction and when that agent should release control to another participant to simulate the turn-taking that takes place in task-oriented, problem-solving interactions. In addition to reasoning about when to take control, an artificial agent (a computational system) must know how to signal what it is doing through its choice of content and linguistic cues. The system must also be able to recognize when the human participant is taking control and reason about whether or not to allow it.
Three problems that I consider are: representing discourse to accommodate conversational role change, reasoning about control, and producing/interpreting linguistic cues that indicate who has control. With my research colleagues at the University of Wisconsin - Milwaukee, I designed and implemented a prototype system that tutors medical students on diagnostic procedures. The system, B2, is being revised this summer as a project of the Natural Language and Knowledge Representation Research Group at the University of Wisconsin - Milwaukee.
Although issues of initiative and control are crucial to the design of effective interactive systems, there is as yet no established community within which one can discuss open questions or propose results. As a result of the last Interactive Systems Grantees Workshop (ISGW '95), a 1997 AAAI Spring Symposium on Computational Models for Mixed Initiative Interaction was organized. This symposium brought together researchers who are interested in developing theoretical and applied models for mixed-initiative interaction. As a result of work presented at the symposium, a special issue of User Modeling User Aided Interaction (UMUAI) will be on mixed-initiative interaction.
"Uniform Knowledge Representation for Language Processing in the B2 System", Susan W. McRoy, Susan Haller, and Syed Ali. To Appear in the Journal of Natural Language Engineering.
"Planning text about plans interactively", Susan Haller, International Journal of Expert Systems Special Issue on Knowledge Representation and Inference for Natural Language Processing, L. Iwanska (ed.),9(1),1996
Traditional plan recognition research deals with bottom-up plan discussions. Bottom-up plan discussions are question-answering dialogues in which the user knows, or thinks she knows most of her domain plan. The system's task is to recognize the user's domain plan from her queries and thereby provide a helpful response. In contrast, interactive text planning is concerned with top-down plan discussions . In top-down plan discussions, the user communicates her intended domain plan to the system because she knows little about how to pursue it. In this context, the system plans discourse (text) to describe and/or recommend a domain plan. While computational models for systems that interact to primarily interpret or generate have been developed, there is little work on integrating these models. I am interested in systems that can relinquish control of an interaction to passively interpret what the user is saying, and take control of the conversation to actively generate natural language that affects what happens next.
Researchers have noted that linguistic devices signal an offer of control to the other participant, or retain control for the current speaker. Researchers have also investigated the role of syntax, intonation, and conversational pragmatics in the construction of turns. Other work has shown how dialogue initiative relates to discourse segmentation boundaries. The model that I am developing incorporates a theory of mixed initiative interaction into a system that accepts and produces natural language text that signals turn-taking.
S. Carberry, Plan Recognition in Natural Language Dialogue. MIT Press, 1990.
A. Cawsey, Explanation and Interaction. MIT Press, 1992.
R.W. Smith and D.R. Hipp. Spoken Natural Language Dialog Systems: A Practical Approach. Oxford University Press, 1994.
J. Moore, Participating in Explanatory Dialogues MIT Press, 1995.
3. Other Communication Modalities.
4. Adaptive Human Interfaces.