Paper: Efficient Dialogue Strategy To Find Users' Intended Items From Information Query Results

ACL ID C02-1152
Title Efficient Dialogue Strategy To Find Users' Intended Items From Information Query Results
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2002
Authors

Weaddressadialogueframeworkthatnarrows downtheuser'squeryresultsobtainedbyanin- formationretrievalsystem. Thefollow-updia- loguetoconstrainqueryresultsissigni cantes- peciallywiththespeechinterfacessuchastele- phonesbecausealotofqueryresultscannotbe presented to the user. The proposed dialogue frameworkgeneratesguidingquestionsbasedon an information theoretic criterion to eliminate retrieved candidates by a spontaneous query withoutassumingasemanticslotstructure. We rstdescribeitsconceptongeneralinformation query tasks, and then deal with a query task ontheappliancemanualwherestructuredtask knowledgeisavailable. Ahierarchical con rma- tion strategyisproposedbymakinguseofatree structure of the manual, and then three cost functions for selecting optimal question nodes arecompared. Experiment...