V. Hung, A. Gonzalez, and R. F. DeMara
University of Central Florida

"Towards A Context-Based Dialog Management Layer for Expert Systems"
in Proceedings of the International Conference on Information, Process, and Knowledge Management, Cancun, Mexico, February 1 – 7, 2009.

Knowledge engineering relies on a unified effort of two components for success: 1) a strong expert knowledge back-end, and 2) an effective user interface. We address the latter issue, identifying the need for intuitive human-computer interface to channel expert knowledge. Speech-based conversation agents describe those computer-based entities that interact with humans to help accomplish a certain task via spoken word input. This paper proposes a method of managing spoken dialog interactions in response to recognizing the human user's goals when accessing an expert system. It is important to note that a set of goals can co-exist during a single conversation, and that each goal may be presented in an asynchronous manner. Such a stipulation exists to enhance the naturalness of the interaction. Inspired by Context-Based Reasoning, the dialog system features a goal management system that ultimately controls the behavior of the expert system.