<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1079">
  <Title>A Text Understander that Learns</Title>
  <Section position="6" start_page="481" end_page="481" type="relat">
    <SectionTitle>
3 Related Work
</SectionTitle>
    <Paragraph position="0"> We are not concerned with lexical acquisition from very large corpora using surface-level collocational data as proposed by Zernik and Jacobs (1990) and Velardi et al. (1991), or with hyponym extraction based on entirely syntactic criteria as in Hearst (1992) or lexico-semantic associations (e.g., Resnik (1992) or Sekine et al.</Paragraph>
    <Paragraph position="1"> (1994)). This is mainly due to the fact that these studies aim at a shallower level of learning (e.g., selectional restrictions or thematic relations of verbs), while our focus is on much more fine-grained conceptual knowledge (roles, role filler constraints, integrity conditions).</Paragraph>
    <Paragraph position="2"> Our approach bears a close relationship, however, to the work of Mooney (1987), Berwick (1989), Rau et al. (1989), Gomez and Segami (1990), and Hastings (1996), who all aim at the automated learning of word meanings from context using a knowledge-intensive approach. But our work differs from theirs in that the need to cope with several competing concept hypotheses and to aim at a reason-based selection in terms of the quality of arguments is not an issue in these studies. Learning from real-world texts usually provides the learner with only sparse and fragmentary evidence, such that multiple hypotheses are likely to be derived and a need for a hypothesis evaluation arises.</Paragraph>
  </Section>
class="xml-element"></Paper>