Dialog Structure and Plan Recognition in Spontaneous Spoken Dialog
CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE
Pagination or Media Count:
In real spoken language applications, speakers interact spontaneously and frequently diverge from the task at hand by initiating various types of domain, application or environmentally related subdialogs. We claim that unconstrained, task-oriented spontaneous spoken dialog is structured and predictable in spite of such phenomena as spurious topic changes and subdialogs. The discourse structure for any specific dialog is derived from the structure of the task, contextual constraints derived from prior interaction and the characteristics of a finite set of discourse plans responsible for subdialogs and topic changes. This paper describes a preliminary model of discourse structure and plan recognition for spontaneous spoken discourse that has been implemented and evaluated on a 5000 utterance test corpora drawn from two distinct spoken language applications. The model dynamically constrains a speech recognizer, simplifies -the process of inferring meaning from a spontaneous spoken utterance and accounts for the subdialog phenomena observed. We describe these discourse plans, constraints on their occurrence and content, and their representation and processing. The model processes all subdialog phenomena using a domain plan tree, a current focus stack and a set of domain tree traversal algorithms.
- Voice Communications