<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1027">
  <Title>PART-OF-SPEECH TAGGING WITH NEURAL NETWORKS</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Words are often ambiguous in their part of speech.</Paragraph>
    <Paragraph position="1"> The English word store for example can be either a noun, a finite verb or an infinitive. In an utterance, this ambiguity is normally resolved by the context of a word: e.g. in the seutence &amp;quot;The 1977 P6's could store two pages of data. &amp;quot;, store can only be an intluitive.</Paragraph>
    <Paragraph position="2"> A part-of-speech tagger is a system which automatically assigns the part of speech to words using contextual information. Potential applications for part-of-speech taggers exist in many areas inclnding speech recognition, speech synthesis, machine translation and information retrieval.</Paragraph>
    <Paragraph position="3"> l)ifi'ereut methods have been used for the im plemenration of part-of-speech taggers. TAGGIT (Greene, Rnbin, 1971), an early system, which was used for the initial tagging of the Brown corpus was rule-based. It was able to assign the correct part-of-speech to about 77 % of the words in the Brown corpus.</Paragraph>
    <Paragraph position="4"> In another approach contextual dependencies are modelled statistically. Churcb (1988) and Kempe (1993) use second order Markov Models and train their systems on large handtagged corpora. Using this metbod, they are able to tag more than 96 % of their test words with the correct part-of-speech. The need for reliably tagged training data, however, is a problem for languages, where such data is not available in sufficient quantities. Jelinek (1985) and Cutting et al. (1992) circumvent this problem by training their taggers on untagged data using tile Itaum-Welch algorithm (also know as the forward-backward algorithm).</Paragraph>
    <Paragraph position="5"> They report rates of correctly tagged words which are comparable to that presented by Church (1988) and Kempe (1993).</Paragraph>
    <Paragraph position="6"> A third and rather new approach is tagging with artificial neural networks. In the area of speech recognition neural networks have been used for a decade r, ow. They have shown performances comparable to that of IIidden Ivlarkov model systems or even better (Lippmann, 1989). Part-of-speech prediction is another area, closer to POS tagging, where neural networks have been applied successfidly. Nakamura el; al. (1990) trained a d-layer feed-forward network with up to three preceding part-of-speech tags ,as input to predict the word category of the next word. The prediction accuracy was similar to that of a trigram-b,~sed predictor. Using tile predictor, Nakamura et al. were able to improve the recognition rate of their speech recognition system from 81.0 % to 86.9 %.</Paragraph>
    <Paragraph position="7"> Federici and Pirrelli (199a) developed a part-of-speech tagger which is based on a special type of neural network. It disambiguates between alternative morphosyntactic tags which are generated by a roof phological analyzer. The tagger is trained with an analogy-driven learning procedure. Only preliminary results are presented, so that a comparison with other methods is difficult.</Paragraph>
    <Paragraph position="8"> Ill this paper, a part-of-speech tagger based on a multilayer perceptrou network is presented. It is similar to tile network of Nakamura et al. (1990) in so far as the same training procedure (Backpropagation) is used; but it differs in the structure of tile network and also in its purpose (disambignation vs. prediction).</Paragraph>
    <Paragraph position="9"> The performance of tl,e presented tagger is measured and compared to that of two other taggers (Cutting et al., 1992; Kempe, 1993).</Paragraph>
  </Section>
class="xml-element"></Paper>