<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1205">
  <Title>Look-Back and Look-Ahead in the Conversion of Hidden Markov Models into Finite State Transducers</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
\[DET, PRO\] \[ADJ,NOUN\] \[ADJ,NOUN\] ...... \[END\] (i)
DET ADJ NOUN ...... END
</SectionTitle>
    <Paragraph position="0"> aThere are other (dillerent) algorithms for HMM to FST conversion: An unpublished one by Julian M.</Paragraph>
    <Paragraph position="1"> Kupiec and John T. Maxwell (p.c.), and n-type and s-type approximation by Kempe (1997).</Paragraph>
    <Paragraph position="2"> The main advantage of transforming an HMM is that the resulting transducer can be handled by finite state calculus. Among others, it can be composed with transducers that encode: * correction rules for the most frequent tagging errors which are automatically generated (Brill, 1992; Roche and Schabes, 1995) or manually written (Chanod and Tapanainen, 1995), in order to significantly improve tagging accuracy -9 . These rules may include long-distance dependencies not handled by ttMM taggers, and can conveniently be expressed by the replace operator (Kaplan and Kay, 1994; Karttunen, 1995; Kempe and Karttunen, 1996).</Paragraph>
    <Paragraph position="3"> * further steps of text analysis, e.g. light parsing or extraction of noun phrases or other phrases (Ait-Mokhtar and Chanod, 1997).</Paragraph>
    <Paragraph position="4"> These compositions enable complex text analysis to be performed by a single transducer.</Paragraph>
    <Paragraph position="5"> The speed of tagging by an FST is up to six times higher than with the original HMM.</Paragraph>
    <Paragraph position="6"> The motivation for deriving the FST from an HMM is that the tIMM can be trained and converted with little manual effort.</Paragraph>
    <Paragraph position="7"> An HMM transducer builds on the data (probability matrices) of the underlying HMM. The accuracy of this data has an impact on the tagging accuracy of both the HMM itself and the derived transducer. The training of the HMM can be done on either a tagged or untagged corpus, and is not a topic of this paper since it is exhaustively described in the literature (Bahl and Mercer, 1976; Church, 1988).</Paragraph>
    <Paragraph position="8"> An HMM can be identically represented by a weighted FST in a straightforward way. We are, however, interested in non-weighted transducers.</Paragraph>
    <Paragraph position="9"> 2Automatically derived rules require less work than manually written ones but are unlikely to yield better results because they would consider relatively limited context and simple relations only.</Paragraph>
    <Paragraph position="10"> Kempe 29 Look-Back and Look-Ahead in the Conversion of HMMs Andr~ Kempe (1998) Look-Back and Look-Ahead in the Conversion of Hidden Markov Models into Finite State Transducers. In D.M.W. Powers (ed.) NeMLaP3/CoNLL98: New Methods in Language Processing and Computational Natural Language Learning, ACL, pp 29-37.</Paragraph>
  </Section>
class="xml-element"></Paper>