<?xml version="1.0" standalone="yes"?>
<Paper uid="W93-0310">
  <Title>Computation of Word Associations Based on the Co-Occurences of Words in Large Corpora I</Title>
  <Section position="8" start_page="633" end_page="633" type="concl">
    <SectionTitle>
7 Discussion and conclusion
</SectionTitle>
    <Paragraph position="0"> In the simulation results a bias towards syntagmatic associations was found. Since the associations were computed from co-occurences of words in texts, this preference of syntagmatic associations is not surprising. It is remarkable, instead, that many associations usually considered to be paradigmatic are predicted correctly. Examples include man -- woman, black ~ white and bitter ~ sweet. We believe, however, that the tendency to prefer syntagmatic associations can be reduced by not counting co-occurences found within collocations.</Paragraph>
    <Paragraph position="1"> Equivalently, the association strength between word pairs always occuring together in a strict formation (separated by a constant number of other words) could be reduced.</Paragraph>
    <Paragraph position="2"> When going from English to German, the parameters /~ and '7 in equation 6 needed to be readjusted in such a way, that less frequent words obtained a better chance to be associated. This reflects the fact, that there is more variation in the associative responses of German than of American subjects, and that American subjects tend to respond with words of higher corpus frequency. We believe that by considering additional languages this parameter adjustment could be predicted from word-frequency-distribution.</Paragraph>
    <Paragraph position="3"> In conclusion, the results show, that free word associations for English and German can be successfully predicted by an almost identical algorithm which is based on the co-occurence-frequencies of words in texts. Some peculiarities in the associative behavior of the subjects were confirmed in the simulation. Together, this is a good indication that the learning of word associations is governed by the law of association by contiguity.</Paragraph>
    <Paragraph position="4"> Although our simulation results are not perfect, specialized versions of our program have already proved useful in a number of applications: * Information Retrieval: Generation of search terms for document retrieval in bibliographic databases (Wettler &amp; Rapp, 1989, Ferber, Wettler &amp; Rapp, 1993).</Paragraph>
    <Paragraph position="5"> * Marketing: Association norms are useful to predict what effects word usage in advertisements has on people (Wettler &amp; Rapp, 1993). Muitilingual assocation norms help to find a global marketing strategy in international markets (Kroeber-Riel, 1992).</Paragraph>
    <Paragraph position="6"> * Machine Translation: In an experimental prototype we have shown that associations derived from context are useful to find the correct translations for semantically ambiguous words.</Paragraph>
    <Paragraph position="7"> The successful prediction of different types of verbal behavior on the basis of co-occurrences of words in texts is a direct application of the classical contiguity-theory, or, in more modern neurophysiological terms, of Hebb's learning rule. Cognitive psychology has severely criticized contiguity-theory with the arguments that association theory did not produce useful results (Jenkins, 1974), and that associations are not the result of associative learning but of underlying semantic processes (Clark, 1970). Both arguments need a critical revision. Recent work with large corpora as well as a large number of connectionist studies have yielded very useful results in different psychological domains, and the high predictive power of the associationist approach makes that the intuitive appeal of cognitivist explanations is fading rapidly.</Paragraph>
  </Section>
class="xml-element"></Paper>