<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2008">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Towards Conversational QA: Automatic Identification of Problematic Situations and User Intent [?]</Title>
  <Section position="8" start_page="63" end_page="63" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper presents our initial investigation on automatic identification of problematic situations and user intent in interactive QA. Our results have shown that, once users are motivated in finding specific information related to their information goals, user behavior and interaction context can help automatically identify problematic situations and user intent. Although our current investigation is based on the data collected from a controlled study, the same approaches can be applied during online processing as the question answering proceeds. The identified problematic situations and/or user intent will provide immediate feed-back for a QA system to adjust its behavior and adapt better strategies to cope with different situations. This is an important step toward intelligent conversational question answering.</Paragraph>
  </Section>
class="xml-element"></Paper>