<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1049">
  <Title>A Report of Recent Progress in Transformation-Based Error-Driven Learning*</Title>
  <Section position="10" start_page="259" end_page="260" type="concl">
    <SectionTitle>
7. CONCLUSIONS
</SectionTitle>
    <Paragraph position="0"> In this paper, we have described a number of extensions to previous work in rule-based part of speech tagging, including the ability to make use of lexical relationships previously unused in tagging, a new method for tagging unknown words, and a way to increase accuracy by returning more than one tag per word in some instances.</Paragraph>
    <Paragraph position="1"> We have demonstrated that the rule-based approach obtains performance comparable to that of stochastic taggets on unknown word tagging and better performance on known word tagging, despite the fact that the rule-based tagger captures linguistic information in a small number of simple non-stochastic rules, as opposed to * 14Unfortunately, it is difficult to find results to compare these k-best tag results to. In \[DeMarcken 90\], the test set is included in the training set, and so it is difficult to know how this system would do on fresh text. In \[Weischedel et al. 93\], a k-best tag experiment was run on the Wall Street Journal corpus. They quote the average number of tags per word for various threshold settings, but do not provide accuracy results.</Paragraph>
    <Paragraph position="2">  large numbers of lexical and contextual probabilities.</Paragraph>
    <Paragraph position="3"> Recently, we have begun to explore the possibility of extending these techniques to both learning pronunciation networks for speech recognition and to learning mappings between sentences and semantic representations.</Paragraph>
  </Section>
class="xml-element"></Paper>