<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1031">
  <Title>Corpus-based Discourse Understanding in Spoken Dialogue Systems</Title>
  <Section position="9" start_page="7" end_page="7" type="concl">
    <SectionTitle>
8 Summary and Future Work
</SectionTitle>
    <Paragraph position="0"> We proposed a new discourse understanding method that orders multiple dialogue states created from multiple dialogue states and the succeeding speech understanding results based on statistical information obtained from dialogue corpora. The results of the experiments show that our approach is effective in reducing the cost of creating the discourse understanding component, and the advantage of keeping multiple dialogue states was also shown.</Paragraph>
    <Paragraph position="1"> There still remain several issues that we need to explore. These include the use of statistical information other than the probability of a dialogue act type sequence and the collocation probability of dialogue states and dialogue acts, the optimization of weighting factors a, b, g, other default parameters that we used in the experiments, and more experiments in larger domains. Despite these issues, the present results have shown that our approach is promising.</Paragraph>
  </Section>
class="xml-element"></Paper>