<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3807">
  <Title>Learning of Graph-based Question Answering Rules</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> In this paper we present a graph-based approach to question answering. The method assumes a graph representation of question sentences and text sentences.</Paragraph>
    <Paragraph position="1"> Question answering rules are automaticallylearntfromatrainingcorpusofques- null tions and answer sentences with the answer annotated. The method is independentfromthegraphrepresentationformal- null ism chosen. A particular example is presented that uses a specific graph representation of the logical contents of sentences.</Paragraph>
  </Section>
class="xml-element"></Paper>