File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/98/w98-0720_concl.xml

Size: 2,105 bytes

Last Modified: 2025-10-06 13:58:16

<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-0720">
  <Title>References</Title>
  <Section position="8" start_page="147" end_page="147" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper proposes a method of deriving metonymic coercions by using the information available in WordNet 1.6. The method does not presuppose the availability ofsortal constraints, but rather builds approximations ofsortai information from the knowledge implemented in WordNet. It uses two distinct approaches for knowledge coercion: one that relies on lexico-semantic information, another based on morphological links and unifying logic formulae (LF'rs) inferred from conceptual definitions.</Paragraph>
    <Paragraph position="1"> To evaluate this methodology of deriving metonymic coercions, a test set of 20 New York Times articles were parsed by FASTUS (Appelt et al., 1993) and used in conjunction with their coreference keys, as provided by the MUC test data. There were 1261 nominal expressions, distributed in four classes as illustrated in Table 1. A percentage of 23% nominals were anaphoric, out of which almost 74% had literal meaning. In approximating the sortal constraints, sorts for 68.2% of nominals were returned. When the sorts were not satisfied by searches through Word-Net, metonymic paths were derived. As Table I indicates, 68.9% of these paths were lexico-semantic (denoted with r=-referential metonymies) and 31.1% were morpho-logical (denoted with p=predicative metonymies).</Paragraph>
    <Paragraph position="2">  The evaluation of path-validating anaphorae against coreference keys resulted in a precision rate of 76% and a recall of 83%. These results indicate that we need to experiment with different similarity measures. We also found that the metonymies have a significant contribution as knowledge sources for coreference resolution. 43% of the coreference keys were accounted by mere string matches. 3.1% by synonyms encoded in WordNet. 3.7% by hypernyms and 16.3% by links made possible through coercions. null</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML