<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1152">
  <Title>Ecient Dialogue Strategy to Find Users' Intended Items from Information Query Results</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Weaddressadialogueframeworkthatnarrows  downtheuser'squeryresultsobtainedbyaninformationretrievalsystem. Thefollow-updialoguetoconstrainqueryresultsissignicantes- null  peciallywiththespeechinterfacessuchastelephonesbecausealotofqueryresultscannotbe null 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 conrmation strategyisproposedbymakinguseofatree structure of the manual, and then three cost functions for selecting optimal question nodes arecompared. Experimentalevaluationdemonstrates that the proposed system helps users ndtheirintendeditemsmoreeciently.</Paragraph>
  </Section>
class="xml-element"></Paper>