<?xml version="1.0" standalone="yes"?>
<Paper uid="E93-1028">
  <Title>Similarity between Words Computed by Spreading Activation on an English Dictionary</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A text is not just a sequence of words, but it also has coherent structure. The meaning of each word in a text depends on the structure of the text. Recognizing the structure of text is an essential task in text understanding.\[Grosz and Sidner, 1986\] One of the valuable indicators of the structure of text is lexical cohesion.\[Halliday and Hasan, 1976\] Lexical cohesion is the relationship between words, classified as follows:  1. Reiteration: Molly likes cats. She keeps a cat.</Paragraph>
    <Paragraph position="1"> 2. Semantic relation: a. Desmond saw a cat. It was Molly's pet.</Paragraph>
    <Paragraph position="2"> b. Molly goes to the north. Not east.</Paragraph>
    <Paragraph position="3"> c. Desmond goes to a theatre. He likes films.  Reiteration of words is easy to capture by morphological analysis. Semantic relation between words, which is the focus of this paper, is hard to recognize by computers.</Paragraph>
    <Paragraph position="4"> We consider lexical cohesion as semantic similarity between words. Similarity is Computed by spreading activation (or association) \[Waltz and Pollack, 1985\] on a semantic network constructed systematically from an English dictionary. Whereas it is edited by some lexicographers, a dictionary is a set of associative relation shared by the people in a linguistic community.</Paragraph>
    <Paragraph position="5"> The similarity between words is a mapping a: Lx L ---* \[0, 1\], where L is a set of words (or lexicon). The following examples suggest the feature of the similarity: a(cat, pet) = 0.133722 (similar), a(cat, mat) = 0.002692 (dissimilar).</Paragraph>
    <Paragraph position="6"> The value of a(w, w') increases with strength of semantic relation between w and w'.</Paragraph>
    <Paragraph position="7"> The following section examines related work in order to clarify the nature of the semantic similarity. Section 3 describes how the semantic network is systematically constructed from the English dictionary. Section 4 explains how to measure the similarity by spreading activation on the semantic network. Section 5 shows applications of the similarity measure -computing similarity between texts, and measuring coherence of a text. Section 6 discusses the theoretical aspects of the similarity.</Paragraph>
  </Section>
class="xml-element"></Paper>