A Connectionist Approach to Content Access in Documents: Application to Detection of Jokes

  • Stephane Zrehen
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 50)


This paper addresses the question of accessing the content of documents. Drawing from similarities between vision and language, a connectionist architecture was designed that can use context information for the “understanding” of content. The principles of the approach are illustrated by the problem of understanding jokes.


Actual Recognition Feature Detector Visual Scene Grammatical Form Connectionist Approach 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alshawi, H. (1990). Resolving quasi logical form, computational linguistics. Computational Linguistics, 16:133–144.Google Scholar
  2. 2.
    Arbib, M. (1989). The Metaphorical Brain 2. John Wiley and Sons, New-York.MATHGoogle Scholar
  3. 3.
    Barnden, J. (1995). Semantic networks. In The Handbook of Brain Theory and Neural Networks, pages 854–857, Cambridge. MIT Press.Google Scholar
  4. 4.
    Barwise, J. and Perry, J. (1983). Situations and Attitudes. MIT-Press, Bradford Books, Cambridge.Google Scholar
  5. 5.
    Biederman, I. (1981). On the semantics of a scene at a glance. In Kubovy, M. and Pomerantz, J., editors, Perceptual Organization, pages 213–253. Lawrence Erlbaum, Hillsdale, New-Jersey.Google Scholar
  6. 6.
    Biederman, I. (1987). Recognition-by-components: A theory of human image understanding. Psychological Review, 94:115–147.CrossRefGoogle Scholar
  7. 7.
    Burl, M., Leung, T., and Perona, P. (1995). Face localization via shape statistics. In Int. Workshop Face and Gesture Recognition. Zurich, Switzerland.Google Scholar
  8. 8.
    Clack, C, Farringdon, J., Lidwell, P., and Yu, T. (1997). Autonomous document classification for business. In Proceedings of the First International Conference on Autonomous Agents, pages 201–207. ACM Press.CrossRefGoogle Scholar
  9. 9.
    Clevenger, T. and Edwards, R. (1988). Semantic distance as a predictor of metaphor selection. Journal of Psycholinguistic Research, 17(3):211–226.CrossRefGoogle Scholar
  10. 10.
    Collins, A. M. and Loffcus, E. (1975). A spreading-activation theory of semantic processing. Psychological Review, 6:407–428.CrossRefGoogle Scholar
  11. 11.
    Croft, W. B. and Thomson, W. (1987). I3r: A new approach to the design of document retrieval systems. Journal of the American Society for Information Science, 38(6):389–404.CrossRefGoogle Scholar
  12. 12.
    Davies, E. (1997). Machine Vision. Academic Press, New-York.Google Scholar
  13. 13.
    Fayyad, U. and G. Piatetsky-Shapiro, e. a. (1996). From data mining to knowledge discovery: An overview. In Fayyad, U., Piatetsky-Shapiro, G., Smyth, P., and Uthurusamy, R., editors, Advances in knowledge Discovery and Data Mining. AAAI Press/IEEE Press, Menlo Park.Google Scholar
  14. 14.
    Freud, S. (1905). Jokes and Their Relations to the Unconscious. Norton, New York.Google Scholar
  15. 15.
    Gaussier, P., Revel, A., Joulain, C, and Zrehen, S. (1996). Living in a partially structured environment: how to bypass the limitations of classical reinforcement techniques. Robotics and Autonomous Systems, 20:225–250.CrossRefGoogle Scholar
  16. 16.
    Grossberg, S. (1988). The art of adaptive pattern recognition by a self-organizing neural network. Computer, March:77–88.Google Scholar
  17. 17.
    Grossberg, S. and Mingolla, E. (1985). Neural dynamics of form perception: Boundary completion, illusory figures and neon color spreading. Psychological Review, 92(2): 173–211.CrossRefGoogle Scholar
  18. 18.
    Jones, W. P. and Furnas, G. W. (1987). Pictures of relevance: A geometric analysis of similarity measures. Journal of the American Society for Information Science, 38(6):420–442.CrossRefGoogle Scholar
  19. 19.
    Kleindorfer, P. L. and et al., H. C. K. (1993). Decision Sciences: An Integrative Perspective. Cambridge University Press, Cambridge.CrossRefGoogle Scholar
  20. 20.
    Lakoff, G. (1987). Women, Fire and Dangerous Things. The University of Chicago Press, Chicago.CrossRefGoogle Scholar
  21. 21.
    Lakoff, G. and Johnson, M. (1980). Metaphors we live by. The University of Chicago Press, Chicago.Google Scholar
  22. 22.
    Pustejovsky, J. (1991). The generative lexicon. Computational Linguistics, 17(4):224–240.Google Scholar
  23. 23.
    Pustejovsky, J. (1994). Linguistic constraints on type coercion. In patrick St-Dizier and Viegas, E., editors, Computational Lexical Semantics. University Press, Cambridge.Google Scholar
  24. 24.
    Quillian, G. (1966). Semantic memory. In Minsky, M., editor, Semantic Information Processing. MIT Press, Cambridge.Google Scholar
  25. 25.
    Rumelhart, D., McClelland, J., and the PDP group (1986). Parallel Distributed Processing. MIT Press, Cambridge.Google Scholar
  26. 26.
    Turney, P. (1996). The identification of context-sensitive features: A formal definition of context for concept learning. In Proceedings of the Workshop on Learning in Context-Sensitive Domains, at the 13th International Conference on Machine Learning, pages 53–59. ICML96, Bari, Italy.Google Scholar
  27. 27.
    y Rita, P. B. (1972). Brain Mechanisms in Sensory Substitution. Academic Press, New-York.Google Scholar
  28. 28.
    Zrehen, S. (1995). Elements of Brain Design for Autonomous Agents. PhD thesis, Swiss Federal Institute of Technology at Lausanne.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Stephane Zrehen
    • 1
  1. 1.Center for Neuromorphic Systems EngineeringCalifornia Institute of TechnologyPasadenaUSA

Personalised recommendations