SYSTEM AND METHOD OF SPOKEN LANGUAGE UNDERSTANDING IN HUMAN COMPUTER DIALOGS

摘要

A system and method are disclosed that improve automatic speech recogniti on in a spoken dialog system. The method comprises partitioning speech recogniz er output into self contained clauses, identifying a dialog act in each of the self contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domai n action, reassigning the another domain action and/or another domain object a s the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.