The Conceptual Content of Conversation.
YALE UNIV NEW HAVEN CONN DEPT OF COMPUTER SCIENCE
Pagination or Media Count:
Conversations between humans constitute a challenging task orientation for theories of natural language processing. Problems of conceptual representation, predictive understanding techniques, and the recognition of conversational continuity are especially crucial for computational models of dialogue. Significant information exchanges often lie hidden beneath the surface communications of human conversation. This paper outlines a strategy for conversational analysis that utilizes multiple levels of information flow in order to characterize the conceptual content of a conversation. The role of predictive knowledge structures and contextual information is illustrated in an analysis of a sample conversation, along with an outline of conversational rules specific to particular levels of conversational analysis. Author