Bytes Tran The research issue is representing and reasoning about interactive discourse during a human-computer natural language interaction. During an interaction, a computational system must be able to take conversational control and release control to another participant to simulate the turn- taking that takes place in task-oriented interactions. In addition to representing and 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 will be addressed in this investigation: reasoning about control, representing discourse to accommodate conversational role change, and producing/interpreting linguistic cues that indicate who has control. Methods that will be applied to development of a model are use of a uniform representation for domain and discourse information, and reification of conversational roles as collaborative modes. As part of the p roposed planning period, a prototype model will be developed, implemented, and evaluated using two different application domains: an interactive spreadsheet and a medical tutoring system. It is unquestioned that natural language is a useful tool for for human- computer interaction. The ability to interact in natural language provides a flexible and efficient means of communication to systems that are becoming increasingly complex to use because of their capabilities
