<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1017">
  <Title>Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates</Title>
  <Section position="8" start_page="0" end_page="0" type="relat">
    <SectionTitle>
6 Related Work
</SectionTitle>
    <Paragraph position="0"> To our knowledge, our work is the flrst effort that systematically explores the in uence of coreferential information of candidates on pronoun resolution in learning-based ways. Iida et al. (2003) also take into consideration the contextual clues in their coreference resolution system, by using two features to re ect the ranking order of a candidate in Salience Reference List (SRL). However, similar to common centering models, in their system the ranking of entities in SRL is also heuristic-based.</Paragraph>
    <Paragraph position="1"> The coreferential chain length of a candidate, or its variants such as occurrence frequency and TFIDF, has been used as a salience factor in some learning-based reference resolution systems (Iida et al., 2003; Mitkov, 1998; Paul et al., 1999; Strube and Muller, 2003). However, for an entity, the coreferential length only reects its global salience in the whole text(s), instead of the local salience in a discourse segment which is nevertheless more informative for pronoun resolution. Moreover, during resolution, the found coreferential length of an entity is often incomplete, and thus the obtained length value is usually inaccurate for the salience evaluation. null</Paragraph>
  </Section>
class="xml-element"></Paper>