<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0212">
  <Title>Using Coreference for Question Answering</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Search engines have become ubiquitous as a means for accessing information. When a ranking of documents is returned by a search engine the information retrieval task is usually not complete. The document, as a unit of information, is often too large for many users information needs and finding information within the set of returned documents poses a burden of its own. Here we examine a technique for extracting sentences from documents which attempts to satisfy the users information needs by providing an answer to the query presented. The system does this by modeling coreference relationships between entities and events in the query and documents. An evaluation of this system is given which demonstrates that it performs better than using a standard tf. idf weighting and that the amount of information that the user must process on average, to find an answer to their query, is reduced by an order of magnitude over document ranking alone.</Paragraph>
  </Section>
class="xml-element"></Paper>