<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-1031">
  <Title>TnT -- A Statistical Part-of-Speech Tagger</Title>
  <Section position="5" start_page="229" end_page="229" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have shown that a tagger based on Markov models yields state-of-the-art results, despite contrary claims found in the literature. For example, the Markov model tagger used in the comparison of (van Halteren et al., 1998) yielded worse results than all other taggers. In our opinion, a reason for the wrong claim is that the basic algorithms leave several decisions to the implementor. The rather large amount of freedom was not handled in detail in previous publications: handling of start- and end-of-sequence, the exact smoothing technique, how to determine the weights for context probabilities, details on handling unknown words, and how to determine the weights for unknown words. Note that the decisions we made yield good results for both the German and the English Corpus. They do so for several other corpora as well. The architecture remains applicable to a large variety of languages.</Paragraph>
    <Paragraph position="1"> According to current tagger comparisons (van Halteren et al., 1998; Zavrel and Daelemans, 1999), and according to a comparsion of the results presented here with those in (Ratnaparkhi, 1996), the Maximum Entropy framework seems to be the only other approach yielding comparable results to the one presented here. It is a very interesting future research topic to determine the advantages of either of these approaches, to find the reason for their high accuracies, and to find a good combination of both.</Paragraph>
    <Paragraph position="2"> TnT is freely available to universities and related organizations for research purposes (see http ://www. coli. uni-sb, de/-thorsten/tnt).</Paragraph>
  </Section>
class="xml-element"></Paper>