File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/97/w97-1305_concl.xml

Size: 2,087 bytes

Last Modified: 2025-10-06 13:57:58

<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-1305">
  <Title>Resolving Anaphoric References on Deficient Syntactic Descriptions</Title>
  <Section position="7" start_page="36" end_page="36" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> Two approaches to robust anaphor resolution have been presented. The first one, which has been implemented, works on fragments of parses representing subtrees which, due to ambiguity or constraint violation, have not been conjoined. The second one has been formally specified. It exploits structural information as far as possible by taking into account dominance relations that are confined to certain readings. Moreover, by producing an exact description of the reading dependency of its decisions, anaphor resolution according to the latter model yields further evidence for structural disambiguation, thereby rendering possible a higher degree of robust processing by allowing structural and referential disambiguation to interact.</Paragraph>
    <Paragraph position="1"> An implementation of the theoretically described approach has to show whether its practical behaviour, which depends on the maximum number of PSF readings n determining the length of the bitvectors, is acceptable. A further generalization is needed for the processing of (truely) fragmentary PSFs in case there is no reading at all. A practically feasible solution might be obtained by combining the two approaches: the theoretically complete method is applied to cope with ambiguity that is clearly confined to certain &amp;quot;local&amp;quot; fragments (e.g. PP attachment within clausal fragments), thereby keeping n small. The heuristic approach handles the remaining cases (e.g. unattached clausal fragments). While a systematic investigation and evaluation of the latter issue is pending, the first results for the practical method confirm that, in accordance with psycholinguistic evidence, high-quality anaphor resolution does not hinge on the availability of a unique syntactic description.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML