<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1050">
  <Title>Improving Japanese Zero Pronoun Resolution by Global Word Sense Disambiguation</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper has incorporated a framework of global word sense disambiguation into a Japanese zero pronoun resolution system. The word sense disambiguation is applied to verbs and nouns. A verb is disambiguated by selecting a corresponding case frame to its context, and a noun is disambiguated by selecting an appropriate semantic feature. Furthermore, the disambiguation results are cached and applied globally. That is to say, it is utilized in the following analyses in the same text. In the future, we will investigate the word sense disambiguation errors further, and expect to improve the system accuracy.</Paragraph>
    <Paragraph position="1"> Appendix A Similarity between examples The similarity between two examples e1,e2 is calculated using the NTT thesaurus as follows:</Paragraph>
    <Paragraph position="3"> where x,y are semantic features, and s1,s2 are sets of semantic markers of e1,e2 respectively.</Paragraph>
    <Paragraph position="4"> lx,ly are the depths of x,y in the thesaurus, and the depth of their lowest (most specific) common node is L. If x and y are in the same node of the thesaurus, the similarity is 1.0, the maximum score based on this criterion.</Paragraph>
    <Paragraph position="5"> B Similarity between case frames Two case frames, F1 and F2, are first aligned according to the agreement of case markers (case slots). Suppose the result of the case slot alignment of F1 and F2 is as follows:</Paragraph>
    <Paragraph position="7"> where Cxx denotes a case slot which contains several case examples. This result means that l case slots are aligned between F1 and F2 and (m [?] l) and (n [?] l) case slots remained in F1 and F2 respectively.</Paragraph>
    <Paragraph position="8"> The similarity between two case slots, C1i and C2i, is the sum of the similarities of case examples as follows:</Paragraph>
    <Paragraph position="10"> where |e1 |and |e2 |represent the frequencies of e1 and e2 respectively.</Paragraph>
    <Paragraph position="11"> The similarities of case slots are summed up with the weight of frequencies of case examples as follows:  Finally, the similarity between case frames is calculated as follows:</Paragraph>
    <Paragraph position="13"/>
  </Section>
class="xml-element"></Paper>