<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1203">
  <Title>I Learning a Lexicalized Grammar for German</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. Introduction
</SectionTitle>
    <Paragraph position="0"> When looking at the most recent advances in syntax theory, one will notice a definite tendency towards lexicalized approaches. Simple context-free grammar formalisms may be easy to handle but they lack the descriptive power to model idiosyncrasies in the syntactic behavior of single words.</Paragraph>
    <Paragraph position="1"> In the natural language learning community, probabilistic approaches play a dominant role. Yet probabilistie learning has its strength in finding major trends in the training data. An idiosyncratic behavior of a single word is very likely to go unnoticed for lack of data. This divergence in interest might be the reason why hardly any attempt was made to have a lexicalized grammar learned.</Paragraph>
    <Paragraph position="2"> In this paper, I will describe an approach to learning a link grammar. Link grammar (Sleator &amp; Temperley 199 I) is highly lexicalized, and therefore the problem of data sparseness will be immense. As a consequence, I have chosen a fuzzy representation. The fuzziness in this case models uncertainty rather than vagueness inherent in the language. The learning algorithm tries to extract as much information as possible from a grammar fragment, partial parses provided by this grammar, and wordclass information (for unknown words or to corroborate decision made by the system).</Paragraph>
  </Section>
class="xml-element"></Paper>