File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/00/c00-1031_concl.xml

Size: 1,692 bytes

Last Modified: 2025-10-06 13:52:45

<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1031">
  <Title>An Empirical Investigation of the Relation Between Discourse Structure and Co-Reference</Title>
  <Section position="8" start_page="212" end_page="213" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> We analyzed empirically the potentials of discourse and linear models of text to determine co-referential links.</Paragraph>
    <Paragraph position="1"> Our analysis suggests that by exploiting the hierarchical structure of texts, one can increase the potential  VT-k models to determine correct co-referential links (0&lt; h&lt; 100).</Paragraph>
    <Paragraph position="2"> q of natural language systems to correctly determine co-referential links, which is a requirement for correctly resolving anaphors. If one treats all discourse units in the preceding discourse equally, the increase is statistically significant only when a discourse-based coreference system looks back at most four discourse units in order to establish co-referential links. However, if one assumes that proximity plays an important role in establishing co-referential links and that referential expressions are more likely to be linked to referees that were used recently in discourse, the increase is statistically significant no matter how many units a discourse-based co-reference sys~ tern looks back in order to establish co-referential links. Acknowledgements. We are grateful to Lynette Hirschman and Nancy Chinchor for making available their corpora of co-reference annotations. We are also grateful to Graeme Hirst for comments and feedback on a previous draft of this paper.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML