<?xml version="1.0" standalone="yes"?>
<Paper uid="J97-1007">
  <Title>An Empirical Study on the Generation of Anaphora in Chinese Ching-Long Yeh* Tatung Institute of Technology</Title>
  <Section position="6" start_page="187" end_page="188" type="concl">
    <SectionTitle>
5. Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we present empirical work on the generation of anaphora in Chinese.</Paragraph>
    <Paragraph position="1"> The initial set of results suggests that most anaphora, including zero anaphora, and full and reduced descriptions for nominal anaphora, can be effectively generated by a rule using simple syntactic, semantic, and discourse constraints. The results obtained from an implementation of this rule, however, correlated less well with human performance. It is hard to determine the reason for this, though the problems of reliably implementing all the constraints, presenting the anaphora within naturalqooking texts and, above all, coping with the disagreements between native speakers, all probably make a contribution.</Paragraph>
    <Paragraph position="2">  Yeh and Mellish An Empirical Study on Anaphora The factors affecting the use of pronouns are very complicated; thus it is difficult to get computable rules. Introducing the constraint of animacy of objects in the rule can resolve part of the problem. We do not handle the generation of long-distance pronouns, which were rare in our texts. A possible solution would be to employ the concept of stacked focus space in Grosz and Sidner's discourse structure theory (Grosz and Sidner 1986; Dale 1992).</Paragraph>
    <Paragraph position="3"> In the final rule, the implementation of the test of the beginning of a discourse segment is not quite as straightforward as the other constraints. In our current implementation, we rely on the hierarchical structure of the message content to be generated as the basis for dividing the message into segments, which is effective in improving the texts generated by our Chinese natural language generation system. The evaluation result also shows that the rule using all constraints collected from the empirical study performs better than one with simpler constraints.</Paragraph>
    <Paragraph position="4"> In the future, this work needs to be further developed to deal with anaphora in other types of texts and the use of connectives in generated text to create cohesive discourse. In addition the constraints for pronominal anaphora could be improved, and the implementation extended to satisfy other types of applications.</Paragraph>
  </Section>
class="xml-element"></Paper>