Abstract noun classification: using a neural network to match word context and word meaning

  • Katja Wiemer-HastingsEmail author
Cognitive Research


Psychologists have used artificial neural networks for a few decades to simulate perception, language acquisition, and other cognitive processes. This paper discusses the use of artificial neural networks in research on semantics—in particular, in the investigation of abstract noun meanings. It is widely acknowledged that a word’s meaning varies with its contexts of use, but it is a complex task to identify which context elements are relevant to a word’s meaning. The present study illustrates how connectionist networks can be used to examine this problem. A simple feedforward network learned to distinguish among six abstract nouns, on the basis of characteristics of their contexts, in a corpus of randomly selected naturalistic sentences.


Discriminant Analysis Word Meaning Output Unit Latent Semantic Analysis Ontological Status 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Anderson, R. C. (1990). Inferences about word meaning. In A. C. Graesser & G. H. Bower (Eds.),Inferences and text comprehension (pp. 1–16). San Diego: Academic Press.Google Scholar
  2. Atchison, J. (1994).Words in the mind. Oxford: Blackwell.Google Scholar
  3. Barsalou, L. W. (1982). Context-independent and context-dependent information in concepts.Memory & Cognition,10, 82–93.CrossRefGoogle Scholar
  4. Barsalou, L. W., &Medin, D. L. (1986). Concepts: Static definitions or context-dependent representations.Cahiers de Psychologie Cognitive,6, 187–202.Google Scholar
  5. Bloom, P. A., &Fischler, I. (1980). Completion norms for 329 sentence contexts.Memory & Cognition,8, 631–642.Google Scholar
  6. Carroll, J. B., Davies, P., &Richman, B. (1971).Word frequency book. Boston: Houghton Mifflin.Google Scholar
  7. Cottrell, W. G. (1989). Toward connectionist semantics. In Y. Wilks (Ed.),Theoretical issues in natural language processing (pp. 64–72). Hillsdale, NJ: Erlbaum.Google Scholar
  8. Eizirik, L. M. R., Barbosa, V. C., &Mendes, S. B. T. (1993). A Bayesiannetwork approach to lexical disambiguation.Cognitive Science,17, 257–283.CrossRefGoogle Scholar
  9. Elshout-Mohr, M., &van Daalen-Kapteijns, M. (1987). Cognitive processes in learning word meanings. In M. G. McKeown & M. E. Curtis (Eds.),The nature of vocabulary acquisition (pp. 53–72). Hillsdale, NJ: Erlbaum.Google Scholar
  10. Fillmore, C. J. (1968). The case for case. In E. Bach & R. T. Harms (Eds.),Universals in linguistic theory (pp. 1–88). New York: Holt, Rinehart & Winston.Google Scholar
  11. Gallant, S. I. (1991) A practical approach for representing context and for performing word sense disambiguity using neural networks.Neural Computation,3, 293–309.CrossRefGoogle Scholar
  12. Goodman, P. (1996).NevProp software, Version 3. Reno: University of Nevada, Washoe Medical Center, Department of Internal Medicine.Google Scholar
  13. Graesser, A. C., &Clark, L. T. (1985).Structures and procedures of implicit knowledge. Norwood, NJ: Ablex.Google Scholar
  14. Graesser, A. C., Swamer, S. S., &Hu, X. (1997). Quantitative discourse psychology.Discourse Processes,23, 229–263.CrossRefGoogle Scholar
  15. Gross, D., &Miller, K. J. (1990). Adjectives in WordNet.International Journal of Lexicography,3, 265–277.CrossRefGoogle Scholar
  16. Hamberger, M. J., Friedman, D., &Rosen, J. (1996). Completion norms collected from younger and older adults for 198 sentence contexts.Behavior Research Methods, Instruments, & Computers,28, 102–108.Google Scholar
  17. Hoeffner, J. H. (1996).Are rules a thing of the past? A single mechanism account of English past tense acquisition and processing. Unpublished doctoral dissertation, Carnegie Mellon University, Pittsburgh.Google Scholar
  18. Katz, J. J., &Fodor, J. A. (1963). The structure of a semantic theory.Language,39, 170–210.CrossRefGoogle Scholar
  19. Kintsch, W. (1988). The role of knowledge in discourse comprehension: A constructive integration model.Psychological Review,95, 163–182.CrossRefPubMedGoogle Scholar
  20. Kintsch, W. (1998).Comprehension: A paradigm for cognition. Cambridge, MA: Cambridge University Press.Google Scholar
  21. Lahav, R. (1989). Against compositionality: The case of adjectives.Philosophical Studies,57, 261–279.CrossRefGoogle Scholar
  22. Landauer, T. K., &Dumais, S. T. (1997). A solution to Plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge.Psychological Review,104, 211–240.CrossRefGoogle Scholar
  23. Landauer, T. K., &Laham, D. (1997, November).Associative production by LSA: The knowledge in words and passages. Paper presented at the 36th Annual Meeting of the Psychonomic Society, Philadelphia.Google Scholar
  24. Lund, K., &Burgess, C. (1996). Producing high-dimensional semantic spaces from lexical co-occurrence.Behavior Research Methods, Instruments, & Computers,28, 203–208.Google Scholar
  25. McClelland, J. L., Rumelhart, D. E., &the PDP Research Group (1986).Parallel distributed processing: Explorations in the microstructure of cognition: Vol. 2. Psychological and biological models. Cambridge, MA: MIT Press.Google Scholar
  26. McKeown, M. G. (1985). The acquisition of word meaning from context by children of high and low ability.Reading Research Quarterly,20, 482–496.CrossRefGoogle Scholar
  27. Mikkulainen, R. (1996). Subsymbolic case-role analysis of sentences with embedded clauses.Cognitive Science,20, 47–73.CrossRefGoogle Scholar
  28. Miller, G. A. (1990). WordNet: An on-line lexical database.International Journal of Lexicography,3, 235–312.CrossRefGoogle Scholar
  29. Miller, G. A. (1991).The science of words. New York: Scientific American Library.Google Scholar
  30. Miller, G. A. &Charles, W. G. (1991). Contextual constraints of semantic similarity.Language & Cognitive Processes,6, 1–28.CrossRefGoogle Scholar
  31. Miller, G. A., &Johnson-Laird, P. N. (1976).Language and perception. Cambridge, MA: Harvard University Press.Google Scholar
  32. Neal, R. M. (1996).Bayesian learning for neural networks. New York: Springer-Verlag.Google Scholar
  33. Rumelhart, D. E., &McClelland, J. L. (1986). On learning the past tenses of English Verbs. In D. E. Rumelhart, J. L. McClelland, & the PDP Research Group,Parallel distributed processing: Explorations in the microstructure of cognition: Vol. 1. Foundations (pp. 216–271). Cambridge, MA: MIT Press.Google Scholar
  34. Rumelhart, D. E., McClelland, J. L., &the PDP Research Group (1986).Parallel distributed processing: Explorations in the microstructure of cognition: Vol. 1. Foundations. Cambridge, MA: MIT Press.Google Scholar
  35. Schank, R. C. (1972). Conceptual dependency: A theory of natural language understanding.Cognitive Psychology,3, 552–631.CrossRefGoogle Scholar
  36. Schwanenflugel, P. J. (1986). Completion norms for final words of sentences using a multiple production measure.Behavior Research Methods, Instruments, & Computers,18, 363–371.Google Scholar
  37. Schwanenflugel, P. J. (1991). Why are abstract concepts hard to understand? In P. J. Schwanenflugel (Ed.),The psychology of word meaning (pp. 223–250). Hillsdale, NJ: Erlbaum.Google Scholar
  38. Schwanenflugel, P. J., &Shoben, E. J. (1983). Differential context effects in the comprehension of abstract and concrete verbal materials.Journal of Experimental Psychology: Learning, Memory, & Cognition,9, 82–102.CrossRefGoogle Scholar
  39. Stahl, S. A. (1991). Beyond the instrumentalist hypothesis: Some relationships between word meanings and comprehension. In P. J. Schwanenflugel (Ed.),The psychology of word meaning (pp. 157–186). Hillsdale, NJ: Erlbaum.Google Scholar
  40. Sternberg, R., &Powell, J. (1983). Comprehending verbal comprehension.American Psychologist,38, 878–893.CrossRefGoogle Scholar
  41. Taylor, W. L. (1953). “Cloze” procedure: A new tool for measuring readability.Journalism Quarterly,30, 415.Google Scholar
  42. Vendler, Z. (1967).Linguistics in philosophy. Ithaca, NY: Cornell University Press.Google Scholar
  43. Waltz, D. L., &Pollack, J. B. (1985). Massively parallel parsing: A strongly interactive model of natural language interpretation.Cognitive Science,9, 51–74.CrossRefGoogle Scholar
  44. Wittgenstein, L. (1953).Philosophical investigations. Oxford: BlackwellGoogle Scholar

Copyright information

© Psychonomic Society, Inc. 1998

Authors and Affiliations

  1. 1.Department of PsychologyThe University of MemphisMemphis

Personalised recommendations