<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1731">
  <Title>Chunking-based Chinese Word Tokenization</Title>
  <Section position="7" start_page="211" end_page="211" type="evalu">
    <SectionTitle>
6 Experimental Results
</SectionTitle>
    <Paragraph position="0"> Table 1 shows the performance of our  The most important advantage of chunking-based Chinese word segmentation is the ability to cope with the unknown words. Table 1 shows that about 75% of the unknown words can be detected correctly using the chunking approach on the PK and CTB corpus.</Paragraph>
  </Section>
class="xml-element"></Paper>