<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1021">
  <Title>A DOP Model for Semantic Interpretation*</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Data-oriented models of language processing embody the assumption that human language perception and production works with representations of concrete past language experiences, rather than with abstract grammar rules. Such models therefore maintain large corpora of linguistic representations of previously occurring utterances. When processing a new input utterance, analyses of this utterance are constructed by combining fragments from the corpus; the occurrence-frequencies of the fragments are used to estimate which analysis is the most probable one.</Paragraph>
    <Paragraph position="1"> * This work was partially supported by NWO, the Netherlands Organization for Scientific Research (Priority Programme Language and Speech Technology).</Paragraph>
    <Paragraph position="2"> For the syntactic dimension of language, various instantiations of this data-oriented processing or &amp;quot;DOP&amp;quot; approach have been worked out (e.g. Bod (1992-1995); Charniak (1996); Tugwell (1995); Sima'an et al. (1994); Sima'an (1994; 1996a); Goodman (1996); Rajman (1995ab); Kaplan (1996); Sekine and Grishman (1995)). A method for extending it to the semantic domain was first introduced by van den Berg et al. (1994). In the present paper we discuss a computationally effective version of that method, and an implemented system that uses it. We first summarize the first fully instantiated DOP model as presented in Bod (1992-1993). Then we show how this method can be straightforwardly extended into a semantic analysis method, if corpora are created in which the trees are enriched with semantic annotations. Finally, we discuss an implementation and report on experiments with two semantically analyzed corpora (ATIS and OVIS).</Paragraph>
  </Section>
class="xml-element"></Paper>