<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-1301">
  <Title>Resolving Bridging References in Unrestricted Text</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"> We presented our most recent results concerning the resolution of bridging descriptions. We identified different types of bridging descriptions, and we proposed a treatment for each of them separately.</Paragraph>
    <Paragraph position="1"> We presented some preliminary experiments with WordNet. Our experience was mixed. WordNet was useful in determining the type of entity for some of the proper names in our corpus, typically cities, states and countries. On the other hand, WordNet proved to be unreliable for the automatic identification of possible link relations, as too many false positives were found. A 'blind' WordNet search for semantic relations is also very expensive computationally. A mechanism for focus tracking (Grosz and Sidner, 1986) or a clustering algorithm should be applied first in order to minimise the costs.</Paragraph>
    <Paragraph position="2"> In order to have proper names available for resolution of future references, it is useful to create discourse referents for them which contain their entity types. Up to now we have identified an entity type for 69% of the names in our corpus, and we resolved 53% of the DDs referring back to proper names with the help of WordNet.</Paragraph>
    <Paragraph position="3"> Pre-modifiers in compound nouns may license the use of definite descriptions. We have presented some preliminary tests that should be further developed.</Paragraph>
    <Paragraph position="4"> Cases of bridging references based on events or propositions usually involve common-sense reasoning; some of them (in our corpus, 34% of all cases based on events) can however be solved by transforming verbs into their nominalizations and then searching for a semantic relation.</Paragraph>
    <Paragraph position="5"> We also claimed that the same problem of determining a linking relation for bridging descriptions holds for first mention uses of DD based on restrictive post-modification.</Paragraph>
    <Paragraph position="6"> As an estimate, we could say that about 60% of the cases in the bridging class could be treated by developing the ideas proposed here. We combined the proposed heuristics with the first version of our system-- we applied the heuristics for proper names, compound nouns and WordNet consult (in this order) to the cases which the system did not handle before. The impact on the overall system performance was an increase in recall from 56% to 65% (note that the bridging class is a small class compared to the others) but precision decreased from 84% to 82%. The heuristics should be further developed, and their integration into the system should be worked out in more detail--the heuristics could be implemented in parallel or through a decision tree.</Paragraph>
    <Paragraph position="7"> Acknowledgements The authors would fike to thank Kjetil Strand and the anonymous referees for their comments on cartier drafts of the paper. The authors are supported by an EPSRC Advanced Fellowship, a CNPq studentship and an EPSRC studentship, respectively.</Paragraph>
  </Section>
class="xml-element"></Paper>