<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-1007">
  <Title>Answering Definition Questions Using Multiple Knowledge Sources</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> To date, research in question answering has concentrated on factoid questions such as &amp;quot;Who was Abraham Lincoln married to?&amp;quot; The standard strategy for answering these questions using a textual corpus involves a combination of information retrieval and named-entity extraction technology; see (Voorhees, 2002) for an overview. Factoid questions, however, represent but one facet of question answering, whose broader goal is to provide humans with intuitive information access using natural language.</Paragraph>
    <Paragraph position="1"> In contrast to factoid questions, the objective for &amp;quot;definition&amp;quot; questions is to produce as many useful &amp;quot;nuggets&amp;quot; of information as possible. For example, the answer to &amp;quot;Who is Aaron Copland?&amp;quot; might include the following: American composer wrote ballets and symphonies born in Brooklyn, New York, in 1900 son of a Jewish immigrant American communist civil rights advocate Until recently, definition questions remained a largely unexplored area of question answering. Standard factoid question answering technology, designed to extract single answers, cannot be directly applied to this task. The solution to this interesting research challenge will draw from related fields such as information extraction, multi-document summarization, and answer fusion.</Paragraph>
    <Paragraph position="2"> In this paper, we present an approach to answering definition questions that combines knowledge from three sources. We present results from our own component analysis and the TREC 2003 Question Answering Track.</Paragraph>
  </Section>
class="xml-element"></Paper>