<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-2008">
  <Title>Improving the Accuracy of Subcategorizations Acquired from Corpora</Title>
  <Section position="7" start_page="8" end_page="8" type="concl">
    <SectionTitle>
5 Concluding Remarks and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper, I presented a method to improve the quality of SCFs acquired from corpora using existing lexicon resources. I applied my method to SCFs acquired from corpora using lexicons of the XTAG English grammar and the LinGO ERG, and have shown that it can eliminate implausible SCFs, preserving more reliable SCFs.</Paragraph>
    <Paragraph position="1"> In the future, I need to evaluate the quality of the resulting SCFs by manual analysis and by using the extended lexicons to improve parsing. I will investigate other clustering methods such as hierarchical clustering, and use other information for clustering such as semantic preference of arguments of SCFs to have more accurate clusters.</Paragraph>
  </Section>
class="xml-element"></Paper>