<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1017">
  <Title>Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper we have proposed a model which incorporates coreferential information of candidates to improve pronoun resolution. When evaluating a candidate, the model considers its adjacent antecedent by describing its properties in terms of backward features. We flrst examined the efiectiveness of the model by applying it in an optimal environment where the closest antecedent of a candidate is obtained correctly. The experiments show that it boosts the success rate of the baseline system for both MUC-6 (4.7%) and MUC-7 (3.5%). Then we proposed how to apply our model in the real resolution where the antecedent of a non-pronoun is found by an additional non-pronoun resolution module. Our model can still produce Success improvement (4.7% for MUC-6 and 1.8% for MUC-7) against the baseline system, despite the low recall of the non-pronoun resolution module.</Paragraph>
    <Paragraph position="1"> In the current work we restrict our study only to pronoun resolution. In fact, the coreferential information of candidates is expected to be also helpful for non-pronoun resolution. We would like to investigate the in uence of the coreferential factors on general NP reference resolution in our future work.</Paragraph>
  </Section>
class="xml-element"></Paper>