<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1059">
  <Title>Finite State Transducers Approximating Hidden Markov Models</Title>
  <Section position="11" start_page="464" end_page="465" type="concl">
    <SectionTitle>
6 Conclusion and Future Research
</SectionTitle>
    <Paragraph position="0"> The two methods described in this paper allow the approximation of an HMM used for part-of-speech tagging, by a finite-state transducer. Both methods have been fully implemented.</Paragraph>
    <Paragraph position="1"> The tagging speed of the transducers is up to five times higher than that of the underlying HMM.</Paragraph>
    <Paragraph position="2"> The main advantage of transforming an HMM is that the resulting FST can be handled by finite 9A maximal length of three classes is not considered here because of the high increase in size and a low increase in accuracy.</Paragraph>
    <Paragraph position="4"> state calculus 1deg and thus be directly composed with other transducers which encode tag correction rules and/or perform further steps of text analysis.</Paragraph>
    <Paragraph position="5"> Future research will mainly focus on this possibility and will include composition with, among others: * Transducers that encode correction rules (possibly including long-distance dependencies) for the most frequent tagging errors, ill order to significantly improve tagging accuracy. These rules can be either extracted automatically from a corpus (Brill, 1992) or written manually (Chanod and Tapanainen, 1995).</Paragraph>
    <Paragraph position="6"> * Transducers for light parsing, phrase extraction and other analysis (A'/t-Mokhtar and Chanod, 1997).</Paragraph>
    <Paragraph position="7"> An HMM transducer can be composed with one or more of these transducers in order to perform complex text analysis using only a single transducer. We also hope to improve the n-type model by using look-ahead to the following tags 11.</Paragraph>
  </Section>
class="xml-element"></Paper>