<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1731">
  <Title>Chunking-based Chinese Word Tokenization</Title>
  <Section position="1" start_page="0" end_page="111" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper introduces a Chinese word tokenization system through HMM-based chunking. Experiments show that such a system can well deal with the unknown word problem in Chinese word tokenization.</Paragraph>
    <Paragraph position="1"> The second term in (2-1) is the mutual information between T and . In order to simplify the computation of this term, we assume mutual information independence (2-2):</Paragraph>
    <Paragraph position="3"/>
  </Section>
class="xml-element"></Paper>