<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2501">
  <Title>Strategies for Advanced Question Answering</Title>
  <Section position="11" start_page="1" end_page="1" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this position paper we discuss several strategies that enhance the pragmatic process involved in the interpretation and resolution of complex questions. In support of our claims we present a Q/A architecture used to benchmark the impact of (1) question decompositions following several criteria; (2) answer fusion which composes a unique, coherent answer from the partial answers extracted for each decomposed question; (3) modeling of user background and (4) processing of negation in questions and/or answers. Additionally, we present a bootstrapping algorithm that enhances the precision of factual Q/A. We argue that each of these enhancements would allow us to advance the state-of-the-art in Q/A and will enable us to correctly process complex questions.</Paragraph>
  </Section>
class="xml-element"></Paper>