<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1004">
  <Title>Learning Dependencies between Case Frame Slots</Title>
  <Section position="6" start_page="24" end_page="24" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> We conclude this paper with the following remarks. null 1. The primary contribution of research reported in this paper is that we ha.ve proposed a method of learning dependencies between case fi'ame slots, which is theoretically somld and elficient, thus 1)roviding au effective tool for acquiriug (;as(' depend(racy information.</Paragraph>
    <Paragraph position="1"> 2. For the sk)t-based too(M, sometimes case slots are found to I)e del)endent. Experimeut.al results demonstrate that using the dependency information, when dependency does exist, structural disambignation results can be improved.</Paragraph>
    <Paragraph position="2"> 3. For the word-based or class-based models, case slots are judged independent, with the data size cm'renl,Iy available in the Penn Tree Bank. This empirical finding verifies the independence assumption widely made in practice in statistical natural language processing. We proposed to use dependency forests to represent case frame pa~terns. It is possible that more complicated probabilistic dependency graphs like Bayesian networks would be more appropriate for representing case frame patterns. This would require even more data and thus the I)roblenl of how to collect sufficient data would be.a crucial issue, in addition to the methodology (ff learning case frame patterns as probabilistic dependency graphs. Finally the problem of how to determine obligatory/optional cases based on dependencies (acquired fi'om data.) should also be addressed.</Paragraph>
  </Section>
class="xml-element"></Paper>