<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1075">
  <Title>A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent Strategy</Title>
  <Section position="8" start_page="2" end_page="3" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper presents a constraint-based multi-agent strategy to coreference resolution of general noun phrases in unrestricted English text.</Paragraph>
    <Paragraph position="1"> The first contribution of this paper comes from the high performance of our system and its easy  The agent for predicate nominal coreference is still under construction. implementation. The second contribution is to filter out indirect and less informative antecedent candidates according to the anaphor type. The third contribution is the differentiation of various coreference types according to the anaphor types and the use of multi-agents.</Paragraph>
    <Paragraph position="2"> Future work includes: * The exploration of new constraints to improve the precision and new coreference types to increase the recall.</Paragraph>
    <Paragraph position="3"> * The problem of type coercion or metonymy which is a general problem and accounts for much of the overall missing recall.</Paragraph>
    <Paragraph position="4"> * The problem of cataphora, which is not handled in the current mechanism.</Paragraph>
  </Section>
class="xml-element"></Paper>