<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1076">
  <Title>Automatic Acquisition of Adjectival Subcategorization from Corpora</Title>
  <Section position="7" start_page="619" end_page="620" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have described a novel system for automatically acquiring adjectival subcategorization and associated frequency information from corpora, along with an annotation tool for producing training and test data for the task. The acquisition system, which is capable of distinguishing 30 SCF types, performs sophisticated pattern matching on sets of GRs produced by a robust statistical parser. The information provided by GRs closely matches the structure that subcategorization acquisition seeks to recover.</Paragraph>
    <Paragraph position="1"> The figures reported demonstrate the feasibility of the approach: our classifier achieved 70% type pre- null cision and 66% type recall on the test data. The discussion suggests several ways in which the system may be improved, refined and extended in the future. null</Paragraph>
  </Section>
class="xml-element"></Paper>