Modeling extemporaneous elaboration

Abstract

Intelligent problem solving systems must be able to express their results in a coherent and flexible manner. One way this can be done is by eztemporaneous elaboration, the method of language production that underlies more skilled tasks such as explanation. This paper outlines a computational model for extemporaneous elaboration that is implemented in a computer model called Extemper, shows examples of its operation, and compares it with other models of language production. Extemper contains the four components minimally required for elaboration: 1) an efficient method for linearizing a knowledge structure, 2) a translation/selection mechanism for producing a conceptual textbase from the knowledge structure, 3) local coherence operators which provide local connections between textbase elements, and 4) a conceptual generator to translate the coherent textbase into English.

Using conversation MOPs in natural language interfaces

“…For example, Extemper, an architecture for extemporaneous elaboration (Bienkowski, 1986), could use conversation MOPs to help it find a linear ordering for parts of an elaboration based on past experience. Conversation MOPs that are associated in memory with a user type could be helpful for altering conversation to fit a user group such as novices or experts.…”