<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1079">
  <Title>A Text Understander that Learns</Title>
  <Section position="7" start_page="481" end_page="481" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have introduced a solution for the semantic acquisition problem on the basis of the automatic processing of expository texts. The learning methodology we propose is based on the incremental assignment and evaluation of the quality of linguistic and conceptual evidence for emerging concept hypotheses. No specialized learning algorithm is needed, since learning is a reasoning task carried out by the classifier of a terminological reasoning system. However, strong heuristic guidance for selecting between plausible hypotheses comes from linguistic and conceptual quality criteria.</Paragraph>
    <Paragraph position="1"> Acknowledgements. We would like to thank our colleagues in the CLIF group for fruitful discussions, in particular Joe Bush who polished the text as a native speaker. K. Schnattinger is supported by a grant from DFG (Ha 2097/3-1).</Paragraph>
  </Section>
class="xml-element"></Paper>