<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0812">
  <Title>Using Semantic Similarity to Acquire Cooccurrence Restrictions from Corpora</Title>
  <Section position="2" start_page="0" end_page="82" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Although the assessment of semantic similarity using a dictionary database as knowledge source has been recognized as providing significant cues for word clustering (Resnik 1995b) and the determination of lexical cohesion (Morris &amp; Hirst, 1991), its relevance for word disambiguation in running text remains relatively unexplored. The goal of this paper is to investigate ways in which semantic similarity can be used to address the disambiguation of syntactic collocates with specific reference to the automatic acquisition of semantic cooccurrence restrictions from text corpora.</Paragraph>
    <Paragraph position="1"> A variety of methods have been proposed to rate words for semantic similarity with reference to an existing word sense bank. In Rada et al. (1989), semantic similarity is evaluated as the shortest path connecting the word senses being compared in a hierarchically structured thesaurus. Kozima &amp; Furugori (1993) Measure conceptual distance by spreading activation on a semantic network derived from LDOCE. Resnik (1995a) defines the semantic similarity between two words as the entropy value of the most informative concept subsuming the two words in a hierarchically structured thesaurus. A comparative assessment of these methods falls outside the scope of this paper as the approach to disambiguation we propose is in principle compatible with virtually any treatment of semantic similarity. Rather, our objective is to show that given a reliable calculation of semantic similarity, good results can be obtained in the disambiguation of words in context. In the work described here, Resnik's approach was used.</Paragraph>
    <Paragraph position="2"> Following Resnik, semantic similarity is assessed with reference to the WordNet lexical database (Miller, 1990) where word senses are hierarchically structured. For example, (all senses of) the nouns clerk and salesperson in WordNet are connected to the first sense of the nouns employee, worker, person so as to indicate that clerk and salesperson are a kind of employee which is a kind of worker which in turn is a kind of person. In this case, the semantic similarity between the words clerk and salesperson would correspond to the entropy value of employee which is the most informative (i.e. most specific) concept shared by the two words. Illustrative extracts of WordNet with specific reference to the examples used throughout the paper are provided in table 1.</Paragraph>
    <Paragraph position="3"> The information content (or entropy) of a concept c --which in WordNet corresponds to a set of such as fire_v_4, dismiss_v_4, terminate_v_4, sack v 2 --- is formally defined as -log p(c) (Abramson, 1963:6-13). The probability of a concept c is obtained for each choice of text corpus or corpora collection K by dividing the frequency of c in K by the total number of words W observed in K which have the same part of speech p as the</Paragraph>
    <Paragraph position="5"> The frequency of a concept is calculated by counting the occurrences of all words which are potential instances of (i.e. subsumed by) the concept. These include words which have the same orthography and part of speech as the synonyms defining the concept as well as the concept's superordinates. Each time a word Wr~is encountered in K, the count of each concepts Cp ~ubsuming Wp (in any of its senses) is increased by one: (2) fieq(cp) = E count(Wp) c. e{x~,sub(x, Wp)} The semantic similarity between two words Wlp W2p is expressed as the entropy value of the most informative concept cp which subsumes both Wlp and W2p, as shown in (3).</Paragraph>
    <Paragraph position="7"> The specific senses of Wlp W2p under which semantic similarity holds is determified with respect to the subsumption relation linking Cp with Wlp ;f2p. Suppose for example that in calculating the semantic similarity of the two verbs fire, dlsmtss using the WordNet lexical database we find that the most informative subsuming concept is represented by the synonym set containing the word sense remove v 2. We will then know that the senses for fire, dismiss under which the similarity holds are fire v 4 and dismiss v 4 as these are the only instances of the verbs fire and dismlss subsumed by remove v 2 in the WordNet hierarchy.</Paragraph>
    <Paragraph position="8"> We propose to use semantic similarity to disambiguate syntactic collocates and to merge disambiguated collocates into classes of cooccurrence restrictions. Disambiguation of syntactic collocates results from intersecting pairs consisting of (i) a cluster containing all senses of a word collocate W1 having appropriate syntactic usage, and (it) a cluster of semantically similar word senses related to W1 by the same syntactic dependency, e.g.:  (4) IN: &lt; {firej_213141617/8},</Paragraph>
    <Paragraph position="10"> OUT: &lt; {fire v_4}, {clerk n_1/2} * The results of distinct disambiguation events are merged into pairs of semantically compatible word clusters using the notion of semantic similarity.</Paragraph>
  </Section>
class="xml-element"></Paper>