<?xml version="1.0" standalone="yes"?>
<Paper uid="W93-0307">
  <Title>Structural Ambiguity and Conceptual Relations</Title>
  <Section position="8" start_page="62" end_page="63" type="concl">
    <SectionTitle>
9. Conclusions
</SectionTitle>
    <Paragraph position="0"> The conceptual association strategy described here leaves room for a number of improvements. The use of mutual information as an association measure, and the weighting of the mutual information score in order to bias the computation in favor of large counts, warrant further consideration -- mutual information has been criticized for, among other things, its poor behavior given low frequencies, and an alternative measures of association may prove better.</Paragraph>
    <Paragraph position="1"> In addition, as noted in the previous section, combining evidence using the paired t-test is problematic, essentially because of word-sense ambiguity. One alternative might be to perform sense disambiguation in advance -- the results of \[Yarowsky, 1993\] demonstrate that a significant reduction in the number of possible noun classifications is possible using only very limited syntactic context, rather than global word co-occurrence statistics. Another related alternative would be to select a single best classification -- for example, using the measure of selectional association proposed in \[Resnik, 1993\] -- rather than considering all possible classifications.</Paragraph>
    <Paragraph position="2"> Another possibility to investigate is the incorporation of structurally-based attachment strategies along with lexical and conceptual association. Such a fusion of structural and iexical preference strategies is suggested in \[Whittemore et al., 1990\], and \[Weischedel et aL, 1989\]  have found that a structural strategy (&amp;quot;closest attachment&amp;quot;) performs well in combination with a class-based strategy, although they use a relatively small, domain-specific taxonomy of classes and assume each word has a pointer to a unique class.</Paragraph>
    <Paragraph position="3"> Still another direction for future work involves the application of similar techniques to other problems like prepositional phrase attachment for which the resolution of ambiguities would seem to require some form of semantic knowledge. 'The problems discussed in \[Church and Patil, 1982\] -- including ambiguous prepositional phrase attachment, noun-noun modification, and coordination m would seem to form a natural class of problems to investigate in this manner. Although there will always be ambiguities that can be resolved only by appeal to complex inferences or highly domain-dependent facts, we believe the combination of domainindependent, knowledge-based resources such as Word-Net with corpus-based statistics may provide the semantic power necessary for solving many instances of such problems, without the need for general reasoning about world knowledge.</Paragraph>
  </Section>
class="xml-element"></Paper>