<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2504">
  <Title>Discourse Structure for Context Question Answering</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> Questions are not asked in isolation, but rather in a cohesive manner that involves a sequence of related questions to meet user's information needs. It is important to understand the role of discourse to support this cohesive question answering.</Paragraph>
    <Paragraph position="1"> By all means, a QA discourse can be represented as coarse as a list of keywords extracted from previous questions or as sophisticated as a fine-grained representation as described in this paper. There is a balance between how much we like to represent the context and how far we can get there.</Paragraph>
    <Paragraph position="2"> Given recent advances in text-based domain independent semantic processing and discourse parsing, as well as the availability of rich semantic knowledge sources, we believe it is the time to start from the other end of the spectrum to examine the possibility and impact of semantic-rich discourse representation for open-domain question answering.</Paragraph>
  </Section>
class="xml-element"></Paper>