<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1080">
  <Title>Self-Organizing D2-gram Model for Automatic Word Spacing</Title>
  <Section position="13" start_page="637" end_page="637" type="evalu">
    <SectionTitle>
CX
</SectionTitle>
    <Paragraph position="0"> 's to achieve this accuracy are</Paragraph>
    <Section position="1" start_page="637" end_page="637" type="sub_section">
      <SectionTitle>
5.4 Effect of Considering Tag Sequence
</SectionTitle>
      <Paragraph position="0"> The state-of-the-art performance on Korean word spacing is to use the hidden Markov model. According to the previous work (Lee et al., 2002), the hidden Markov model shows the best performance when it sees two previous tags and two previous syllables.</Paragraph>
      <Paragraph position="1"> For the simplicity in the experiments, the value for CZ in Equation (3) is set to be one. The performance comparison between normal HMM and the proposed method is given in Table 4.</Paragraph>
      <Paragraph position="2"> The proposed method considers the various number of previous syllables, whereas the normal HMM has the fixed context. Thus, the proposed method in Table 4 is specified as 'self-organizing HMM.' The accuracy of the self-organizing HMM is 94.71%, while that of the normal HMM is just 92.37%. Even though the normal HMM considers more previous tags (CZ BP BE), the accuracy of the self-organizing model is 2.34% higher than that of the normal HMM. Therefore, the proposed method that considers the sequence of word spacing tags achieves higher accuracy than any other methods reported ever.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>