<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-2029">
  <Title>Automatic Derivation of Surface Text Patterns for a Maximum Entropy Based Question Answering System</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Several QA systems have investigated the use of text patterns for QA (Soubbotin and Soubbotin, 2001), (Soubbotin and Soubbotin, 2002), (Ravichandran and Hovy, 2002). For example, for questions like &amp;quot;When was Gandhi born?&amp;quot;, typical answers are &amp;quot;Gandhi was born in 1869&amp;quot; and &amp;quot;Gandhi (1869-1948)&amp;quot;. These examples suggest that the text patterns such as &amp;quot;a3 NAMEa4 was born in a3 BIRTHDATEa4 &amp;quot; and &amp;quot;a3 NAMEa4 (a3 BIRTHDATEa4 a3 DEATHYEARa4 )&amp;quot; when formulated as regular expressions, can be used to select the answer phrase to questions. Another approach to a QA system is learning correspondences between question and answer pairs. IBM's Statistical QA (Ittycheriah et al., 2001a) system uses a probabilistic model trainable from Question-Answer sentence pairs. The training is performed under a Maximum Entropy model, using bag of words, syntactic and name entity features. This QA system does not employ the use of patterns. In this paper, we explore the inclusion of surface text patterns into the framework of a statistical question answering system.</Paragraph>
  </Section>
class="xml-element"></Paper>