@article {16028, title = {Metareasoning for More Effective Human-Computer Dialogue}, year = {2002}, month = {2002/12/31/}, institution = {University of Maryland, College Park}, abstract = {The research project explores specific meta-dialogue behaviors in terms of both how a system could be made to perform them, and to what extent they can increase overall system performance. We focus on two types of meta-dialogue capabilities: ability to detect and recover from anomalous dialogue patterns in simple exchanges, and on-line extensions or changes to working vocabulary. Our main method involves detailed representation of the dialogue context, separating domain, language, and dialogue specific aspects, and significant amounts of meta-reasoning about the system{\textquoteright}s processing of these representations. An existing logical inference system, ALMA/CARNE, developed as part of a pilot study, is being used in an implementation phase of this work. We are also engaged in a study of existing dialogue corpora to investigate the range and frequency of meta-dialogue expressions in different task domains.}, keywords = {*LEARNING MACHINES, COMPUTER LOGIC, COMPUTER PROGRAMMING AND SOFTWARE, CYBERNETICS, MAN COMPUTER INTERFACE, METAREASONING, NATURAL LANGUAGE., PROCESSING}, url = {http://stinet.dtic.mil/oai/oai?\&verb=getRecord\&metadataPrefix=html\&identifier=ADA414209}, author = {Perlis, Don and Anderson,Mike} }