<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0615">
  <Title>I HMM Specialization with Selective Lexicalization*</Title>
  <Section position="7" start_page="125" end_page="127" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we present a method for complementing the Hidden Markov Models. With this method, we lexicalize the Hidden Markov Model seletively and automatically by examining the transition distribution of each state relating to certain words.</Paragraph>
    <Paragraph position="1"> Experimental results showed that the selective lexicalization improved the tagging accurary from about 95.79% to about 96.00%. Using normal tests for statistical significance we found that the improvement is significant at the 95% level of confidence.</Paragraph>
    <Paragraph position="2"> Tile cost for this imt~rovenmnt is minimal.</Paragraph>
    <Paragraph position="3"> The resulting network contains 210 additional lexicalized states which are found automatically. Moreover, the lexicalization will not decrease the tagging speed 2, because the lexicalized states and their corresponding original states are exclusive in our lexicalized network, and thus the rate of ambiguity is not increased even if the lexicalized states are included.</Paragraph>
    <Paragraph position="4"> Our approach leaves much room for improvement. We have so far considered only the outgoing transitions from the target states. As a result, we have discriminated only the words with right-associativity. We could also discriminate the words with left-associativity by examining the incoming transitions to the state. Furthermore, we could extend the context by using the second-order context as represented in Figure l(c). We believe that the same technique presented in this paper could be applied to the proposed extensions.</Paragraph>
    <Paragraph position="6"/>
  </Section>
class="xml-element"></Paper>