<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0206">
  <Title>Pronoun Resolution in Japanese Sentences Using Surface Expressions and Examples</Title>
  <Section position="4" start_page="0" end_page="39" type="intro">
    <SectionTitle>
2 The Framework for Estimating the
Referent
</SectionTitle>
    <Paragraph position="0"> Prior to the pronoun resolution process, sentences are transformed into a case structure by a case structure analyzer (Kurohashi &amp; Nagao 94). The antecedents of pronouns are determined by heuristic rules from left to right. Using these rules, our system assigns points to possible antecedents, and judges that the one having the maximum total score is the desired antecedent.</Paragraph>
    <Paragraph position="1"> Heuristic rules are classified into two kinds: Candidate enumerating rules and Candidate judging rules. Candidate enumerating rules are used in enumerating candidate antecedents and giving them points (which represent the plausibility of being the correct antecedent). Candidate judging rules are used in giving points to the candidate antecedents selected by Candidate enumerating rules. These rules are shown in Figures 1 and 2. Surface expressions, semantic constraints, referential properties, etc. are written as conditions in the Condition part. Possible antecedents are written in the Possible-Antecedent part. Points means the plausibility of the possible antecedent. null An estimation of the referent is performed using the total scores of possible antecedents given by Candidate enumerating rules and Candidate judging rules. First, the system applies all Candidate enumerating rules to the anaphor and enumerates candidate antecedents having points. Next, the system applies aLl Candidate judging rules to all the candidate antecedents and sums the scores of all the candidate antecedents. Consequently,  the system judges the candidate antecedent having the best score to be the proper antecedent. If several candidate referents have the best score, the candidate referent selected first in order 2 is judged to be the correct antecedent.</Paragraph>
    <Paragraph position="2"> We made 50 Candidate enumerating rules and 10 Candidate judging rules for analyzing demonstratives, 4 Candidate enumerating rules and 6 Candidate judging rules for analyzing personal pronouns, and 19 Candidate enumerating rules and 4 Candidate judging rules for analyzing zero pronouns. Some of the rules are described in the following sections.</Paragraph>
  </Section>
class="xml-element"></Paper>