<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1304">
  <Title>Interactive Question Answering and Constraint Relaxation in Spoken Dialogue Systems</Title>
  <Section position="9" start_page="33" end_page="34" type="concl">
    <SectionTitle>
8 Conclusions
</SectionTitle>
    <Paragraph position="0"> We described strategies for selecting and presenting succinct information in spoken dialogue systems. Verbalizing the constraints used in a query is crucial for robustness and usability - in fact, it can be regarded as a special case of providing feed-back to the user about what the system has heard and understood (see (Traum, 1994), for example).</Paragraph>
    <Paragraph position="1">  The specific strategies we use include 'backingoff' to more general constraints (by the system) or suggesting query refinements (to be requested explicitly by the user). Our architecture is configurable and open: it can be parametrized by empirically derived values and extended by new constraint handling techniques and dialogue strategies. Constraint relaxation techniques have widely been used before, of course, for example in syntactic and semantic processing. The presented paper details how these techniques, when used at the content determination level, tie in with dialogue and generation strategies. Although we focussed on the restaurant selection task, our approach is generic and can be applied across domains, provided that the dialogue centers around accessing and selecting potentially large amounts of factual information.</Paragraph>
    <Paragraph position="2"> Acknowledgments This work is supported by the US government's NIST Advanced Technology Program. Collaborating partners are CSLI, Robert Bosch Corporation, VW America, and SRI International. We thank the many people involved in system design, development and evaluation, and the reviewers of this paper.</Paragraph>
  </Section>
class="xml-element"></Paper>