<?xml version="1.0" standalone="yes"?>
<Paper uid="E91-1019">
  <Title>AUTOMATIC LEARNING OF WORD TRANSDUCERS FROM EXAMPLES</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> We have proposed a method for leam-Ing transducers for the tasks of morphological analysis and grapheme-to-phoneme transcription. This method may be favorably compared to others solutions based upon writing rules in the sense that it does not oblige to identify rules, it provides a result which is directly usable as a transducer and it allows to list/~anslations according to a decreasing order of probability. Yet, the learned automaton does not lend itself to an interpretation in the form of symbolic rules - provided that such rules exist -.</Paragraph>
    <Paragraph position="1"> Moreover, some learning parameters are set only as the results of empirical or random choices: number of states, initial probability distribution, etc. Yet, other advantages weigh for the proposed method. The automaton may take into account the whole word to be translated rather than a limited part of it - this Justifies that a set of equivalent symbolic rules is hard to obtain -. For example, the grapheme-to-phoneme transcription may recognize the original language of a word while translating It (Oshlka et al. 1988): the &amp;quot;French&amp;quot; nouns &amp;quot;meeting&amp;quot; and &amp;quot;carpacclo&amp;quot; have kept respectively their original English and Italian form - II1 and pronunciation, etc. The learned automaton is symmetrical, thus it Is also reversible. In other words, the morphological analysis automaton may also be used as a generator and the grapheme-to-phoneme automaton may become a phoneme-to-grapheme transducer. Another remark ts in order: since the automaton is reversible, it may be composed with its inverse to form, for example, a grapheme-to-grapheme translator that keeps the phonemic form constant without actually computing it.</Paragraph>
    <Paragraph position="2"> Now, it has been shown elsewhere (Reape and Thompson 1988) that the transducer that would result is also describable in the formalism of finite state automata and that its number of states has a upper bound which is the square of the number of states in the base automaton. (Reape and Thompson 1988) also describes an algorithm for computing the resulting automaton. Lastly, other functions than morphological analysis or grapheme-to-phoneme transcription may be envisioned like, for example, the decomposition of words into syllables or the computation of abbreviations by contraction. null</Paragraph>
  </Section>
class="xml-element"></Paper>