<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2116">
  <Title>Empirical Acquisition of Differentiating Relations from Definitions</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Large-scale lexicons for computational semantics often lack sufficient distinguishing information for the concepts serving to define words. For example, WordNet (Miller, 1990) recently introduced new relations for domain category and location in Version 2.0, along with 6,000+ instances; however, about 38% of the noun synsets are still not explicitly distinguished from sibling synsets.</Paragraph>
    <Paragraph position="1"> Work on the Extended WordNet project (Harabagiu et al., 1999) is achieving substantial progress in making the information in WordNet more explicit. The main goal is to transform the definitions into a logical form representation suitable for drawing inferences; in addition, the content words in the definitions are being disambiguated. In the logical form representation, separate predicates are used for each preposition, as well as for some other functional words (e.g., conjunctions); thus, ambiguity in the underlying relations implicit in the definitions is not being resolved. The work described here automates the process of relation disambiguation. This can be used to further the transformation of WordNet into an explicit lexical knowledge base.</Paragraph>
    <Paragraph position="2"> Earlier approaches to differentia extraction have predominantly relied upon manually constructed pattern matching rules for extracting relations from dictionary definitions (Vanderwende, 1996; Barri`ere, 1997; Rus, 2002). These rules can be very precise, but achieving broad-coverage can be difficult. Here a broad coverage dependency parser is first used to determine the syntactic relations that are present among the constituents in the sentence. Then the syntactic relations between sentential constituents are converted into semantic relations between the underlying concepts using statistical classification.</Paragraph>
    <Paragraph position="3"> Isolating the disambiguation step from the extraction step in this manner allows for greater flexibility over earlier approaches. For example, different parsers can be incorporated without having to rework the disambiguation process.</Paragraph>
    <Paragraph position="4"> This paper is organized as follows: Section 2 details the steps in extracting the initial relations from the definition parse. Section 3 illustrates the disambiguation process, the crucial part of this approach. Section 4 presents an evaluation of the relations that are extracted from the WordNet definitions. Lastly, Section 5 compares the approach to previous approaches that have been tried.</Paragraph>
  </Section>
class="xml-element"></Paper>