<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1048">
  <Title>Corpus-Based Identification of Non-Anaphoric Noun Phrases</Title>
  <Section position="8" start_page="378" end_page="378" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have developed several methods for automatically identifying existential noun phrases using a training corpus. It accomplishes this task with recall and precision measurements that exceed those of the earlier Vieira &amp; Poesio system, while not exploiting full parse trees, appositive constructions, hand-coded lists, or case sensitive text z. In addition, because the system is fully automated and corpus-based, it is suitable for applications that require portability across domains. Given the large percentage of non-anaphoric discourse entities handled by most coreference resolvers, we believe that using a system like ours to filter existential NPs has the potential to reduce processing time and complexity and improve the accuracy of coreference resolution.</Paragraph>
  </Section>
class="xml-element"></Paper>