<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1011">
  <Title>Evaluating a Focus-Based Approach to Anaphora Resolution*</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Anaphora resolution is still present as a significant linguistic problem, both theoretically and practically, and interest has recently been renewed with the introduction of a quantitative evaluation regime as part of the Message Understanding Conference (MUC) evaluations of Information Extraction (IE) systems (Grishman and Sundheim, 1996). This has made it possible to evaluate different (implementable) theoretical approaches against sizable corpora of real-world texts, rather than the small collections of artificial examples typically discussed in the literature.</Paragraph>
    <Paragraph position="1"> This paper describes an evaluation of a focus-based approach to pronoun resolution (not anaphora in general), based on an extension of Sidner's algorithm (Sidner, 1981) proposed in (Azzam, 1996), with further refinements from development on real-world texts. The approach * This work was carried out in the context of the EU AVENTINUS project (Thumair, 1996), which aims to develop a multilingual IE system for drug enforcement, and including a language-independent coreference mechanism (Azzam et al., 1998).</Paragraph>
    <Paragraph position="2"> is implemented within the general coreference mechanism provided by the LaSIE (Large Scale Information Extraction) system (Gaizauskas et al., 1995) and (Humphreys et al., 1998), Sheffield University's entry in the MUC-6 and 7 evaluations.</Paragraph>
  </Section>
class="xml-element"></Paper>