<?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="4" start_page="0" end_page="232" type="relat">
    <SectionTitle>
2 Related Work on Measuring
Similarity
</SectionTitle>
    <Paragraph position="0"> Words in a language are organized by two kinds of relationship. One is a syntagmatic relation: how the words are arranged in sequential texts. The other is a  &amp;quot;polite&amp;quot; azlgulax I I I '. ~.~ I I rounded veak : : : : ; ~1 I strong rough : : : : : ' ~: : Booth active ' ' ' ~' ....... : passive small I I l~ : l I I large cold .... I , , , : hot good &amp;quot;' ~'I'~' &amp;quot; ; ; I bad fresh ...... I I stale  (semantic differential \[Osgood, 1952\]). paradigmatic relation: how the words are associated with each other. Similarity between words can be defined by either a syntagmatic or a paradigmatic relation.</Paragraph>
    <Paragraph position="1"> Syntagmatic similarity is based on co-occurrence data extracted from corpora \[Church and Hanks, 1990\], definitions in dictionaries \[Wilks etal., 1989\], and so on. Paradigmatic similarity is based on association data extracted from thesauri \[Morris and Hirst, 1991\], psychological experiments \[Osgood, 1952\], and so on.</Paragraph>
    <Paragraph position="2"> This paper concentrates on paradigmatic similarity, because a paradigmatic relation can be established both inside a sentence and across sentence boundaries, while syntagmatic relations can be seen mainly inside a sentence -- like syntax deals with sentence structure. The rest of this section focuses on two related works on measuring paradigmatic similarity -- a psycholinguistic approach and a thesaurus-based approach.</Paragraph>
    <Section position="1" start_page="232" end_page="232" type="sub_section">
      <SectionTitle>
2.1 A Psycholinguistic Approach
</SectionTitle>
      <Paragraph position="0"> Psycholinguists have been proposed methods for measuring similarity. One of the pioneering works is 'semantic differential' \[Osgood, 1952\] which analyses meaning of words into a range of different dimensions with the opposed adjectives at both ends (see Figure 1), and locates the words in the semantic space.</Paragraph>
      <Paragraph position="1"> Recent works on knowledge representation are somewhat related to Osgood's semantic differential. Most of them describe meaning of words using special symbols like microfeatures \[Waltz and Pollack, 1985; Hendler, 1989\] that correspond to the semantic dimensions. null However, the following problems arise from the semantic differential procedure as measurement of meaning. The procedure is not based on the denotative meaning of a word, but only on the connotative emotions attached to the word; it is difficult to choose the relevant dimensions, i.e. the dimensions required for the sufficient semantic space.</Paragraph>
    </Section>
    <Section position="2" start_page="232" end_page="232" type="sub_section">
      <SectionTitle>
2.2 A Thesaurus-based Approach
</SectionTitle>
      <Paragraph position="0"> Morris and Hirst \[1991\] used Roget's thesaurus as knowledge base for determining whether or not two words are semantically related. For example, the semantic relation of truck/car and drive/car are captured in the following way:  1. truck E vehicle B car (both are included in the vehicle class), 2. drive E journey ~ vehicle B car  Oourney refersto vehicle).</Paragraph>
      <Paragraph position="1"> This method can capture Mmost all types of semantic relations (except emotional and situational relation), such as paraphrasing by superordinate (ex. cat/pet), systematic relation (ex. north/east), and non-systematic relation (ex. theatre/fi\]~). However, thesauri provide neither information about semantic difference between words juxtaposed in a category, nor about strength of the semantic relation between words -- both are to be dealt in this paper. The reason is that thesauri axe designed to help writers find relevant words, not to provide the meaning of words.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>