<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1206">
  <Title>Enhancement of a Chinese Discourse Marker Tagger with C4.5</Title>
  <Section position="7" start_page="43" end_page="43" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In order to study discourse markers for use in the automatic summarization of Chinese text, we have designed and implemented the SIFAS system. In this paper, we have focused on the problems of NULL marker location and the classification of RDMs and ADMs. A study on applying machine learning techniques to discourse marker disambiguation is conducted. C4.5 is used to generate decision tree classifiers. Our results indicate that machine learning is an effective approach to improving the accuracy of discourse marker tagging. For interactive use of the system, if we set a threshold for the rule precision and only display those low precision rules for interactive selection, we can greatly speed up the semi-automatic tagging process.</Paragraph>
  </Section>
class="xml-element"></Paper>