Skip to main content
SpringerLink
Log in

Goal/plan analysis via distributed semantic representations in a connectionist system

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

In this paper we describe DYNASTY, a multi-module distributed connectionist system designed to perform a very high-level symbolic task, namely, comprehension of goal/plan-based stories. DYNASTY has two phases of operation: learning and performance. During learning, each DYNASTY module acquires both the knowledge and skill to perform its specified subtask, through backpropagation learning on a data set of propositions. In addition to modifying their connection weights, DYNASTY modules automatically form distributed semantic representations (DSRs) of the lexical and conceptual symbols used in training the modules. Each DSR encodes, as an activation vector, both structural and sequential information inherent in the training data. During performance, DRSs are passed among various connectionist modules, thus supporting communication and modularity. In addition, DSRs of words with similar meanings end up having similar DSRs. This feature gives DYNASTY the ability to generalize, e.g., generate appropriate inferences when given novel yet similar inputs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. S.J. Alvarado,Understanding Editorial Text: A Computer Model of Argument Comprehension,Kluwer Academic, Norwell, MA, 1990.

    Google Scholar 

  2. J.G. Carbonell,Subjective Understanding, Ph.D. dissertation, Computer Science Dept., Yale University, 1979.

  3. R.E. Cullingford, SAM., in R.C. Schank and C.K. Reisbeck (eds.),Inside Computer Understanding: Five Programs Plus Miniatures, Lawrence Erlbaum Assoc., Hillsdale NJ, pp. 75–119, 1981.

    Google Scholar 

  4. M.G. Dyer,In-Depth Understanding: A Computer Model of Integrated Processing for Narrative Comprehension, The MIT Press, Cambridge, MA, 1983.

    Google Scholar 

  5. M.G. Dyer, “Distributed Symbol Formation and Processing in Connectionist Networks,”Journal of Experimental and Theoretical Artificial Intelligence, 2, 215–239, 1990.

    Google Scholar 

  6. M.G. Dyer, “Symbolic Neuroengineering for Natural Language Processing: A Multi-level Research Approach,” in J. Barnden and J. Pollack (eds.),High-Level Connectionist Models, (pp. 32–86), Ablex Publishers, New York, NY, 1991a.

    Google Scholar 

  7. M.G. Dyer, “Connectionism versus Symbolism in High-Level Cognition,” in T. Horgan and J. Tienson (eds.),Connectionism and the Philosophy of Mind, Kluwer Academic Publishers, Boston MA. pp. 382–416, 1991b.

    Google Scholar 

  8. M.G. Dyer, M. Flowers, and Y.A. Wang, “Distributed Symbol Discovery through Symbolc Recirculation: Toward Natural Language processing in Distributed Connectionist Networks,” in R. Reilly and N. Sharkey (eds.),Connectionist Approaches to Natural Language Understanding, Lawrence Erlbaum Assoc. Press, Hillsdale NJ; Chapter 2, pp. 21–48, 1992.

    Google Scholar 

  9. M.G. Dyer and V.I. Nenov, “Language Learning via Perceptual/Motor Experiences,”Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society, Lawrence Erlbaum Assoc., Hillsdale NJ, 1993.

    Google Scholar 

  10. J.L. Elman, “Finding structure in time,”Cognitive Science, 14, 179–211, 1990.

    Google Scholar 

  11. J.A. Feldman, “Neural Representation of Conceptual Knowledge,” in Nadel, Cooper, Culicover and Harnish (eds.),Neural Connections, Mental Computation, MIT Press, Cambridge MA, 1989.

    Google Scholar 

  12. J.A. Hartigan,Clustering Algorithms, John Wiley and Sons, NY, 1975.

    Google Scholar 

  13. G.E. Hinton, J.L. McClelland, and D.E. Rumelhart, “Distributed Representations,” in Rumelhart and McClelland,Parallel Distributed Processing, vol. 1, Bradford Book/MIT Press, 1986.

  14. G.E. Hinton, “Learning Distributed Representations of Concepts,”Proceedings of the Eighth Annual Conference of the Cognitive Science Society, pp. 1–12, Amherst, MA, 1986.

  15. Lee,Distributed Semantic Representations for Goal/Plan Analysis of Narratives in a Connectionist Architecture, (UCLA CS Dept. Ph.D.), 1991.

  16. G. Lee, M. Flowers, and M.G. Dyer, “A Symbolic/Connectionist Script Applier Mechanism,”Proceedings of the Eleventh Annual Conference of the Cognitive Science Society (CogSci-89), Ann Arbor, Michigan, (Lawrence Erlbaum Assoc., Hillsdale NJ), 1989.

    Google Scholar 

  17. G. Lee, M. Flowers, and M.G. Dyer, “Learning Distributed Representations for Conceptual Knowledge and their Application to Script-Based Story Processing,”Connection Science, vol. 2, no. 4, pp. 313–345, 1990.

    Google Scholar 

  18. J.L. McClelland and A.H. Kawamoto, “Mechanisms of Sentence Processing: Assigning Roles to Constituents of Sentences,” in McClelland and Rumelhart (eds.),Parallel Distributed Processing, vol. 2, Cambridge, MA: MIT Press/Bradford Books, 1986.

    Google Scholar 

  19. R. Miikkulainen and M.G. Dyer, “Natural language processing with modular PDP networks and distributed lexicon,”Cognitive Science, 15(3), 343–399, 1991.

    Google Scholar 

  20. R. Miikkulainen and P. Risto,Subsymbolic Natural Language Processing, Bradford Book/MIT Press, Cambridge, MA, 1993.

    Google Scholar 

  21. V.I. Nenov,Perceptually Grounded Language Acquisition: A Neural/Procedural Hybrid Model, Ph.D. Thesis and Technical Report UCLA-AI-91-07, Computer Science Department, UCLA, 1991.

  22. V.I. Nenov and M.G. Dyer, (in press), “Language/Learning via Perceptual/Motor Association: A Massively Parallel Model,” in Hiroaki Kitano (ed.),Massively Parallel Artificial Intelligence, AAAI/MIT Press, Chapter 7, pp. 203–245, 1994.

  23. A. Newell, “Physical Symbol Systems,”Cognitive Science, vol. 2, 1980.

  24. A. Newell, “The Knowledge Level,”AI Magazine, vol. 2, no. 2, pp. 1–20, 1981.

    Google Scholar 

  25. S. Pinker and J. Mehler (eds.),Connections and Symbols, Bradford Books/MIT Press, 1988.

  26. J.B. Pollack, “Recursive distributed representations,”Artificial Intelligence, vol. 46, pp. 77–105, 1990.

    Google Scholar 

  27. D.E. Rumelhart and J.L. McClelland, (eds.),Parallel Distributed Processing, (vols. 1 and 2), Bradford Books/MIT Press, Cambridge MA, 1986.

    Google Scholar 

  28. D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning internal representations by error propagation,” in D.E. Rumelhart and J.L. McClelland, (eds.),Parallel Distributed Processing, vol. 1, Bradford Books/MIT Press, Cambridge MA, 1986.

    Google Scholar 

  29. R.C. Schank and R. Abelson,Scripts, Plans, Goals and Understanding, Hillsdale, NJ, LEA Press, 1977.

    Google Scholar 

  30. P. Smolensky, “On the Proper Treatment of Connectionism,”The Behavioral and Brain Sciences, vol. 11, no. 1, 1988.

  31. St. John, “The story gestalt: A model of knowledge-intensive processes in text comprehension,”Cognitive Science, 16, pp. 271–306, 1992.

    Google Scholar 

  32. D.S. Touretzky and G.E. Hinton, “A Distributed Connectionist Production System,”Cognitive Science, 12(3), pp. 423–466, 1988.

    Google Scholar 

  33. T. van Gelder,Distributed Representation, Ph.D. Graduate Faculty of Art and Science, University of Pittsburgh, PA, 1989.

    Google Scholar 

  34. R. Wilensky,Planning and Understanding: A Computational Approach to Human Reasoning, Addison-Wesley, Reading, MA, 1983.

    Google Scholar 

  35. U. Zernik and M.G. Dyer, “The Self-Extending Phrasal Lexicon,”Computational Linguistics, vol. 13, nos. 3–4, pp. 308–327, 1987.

    Google Scholar 

  36. T. Kohonen,Self-Organization and Association Memory, Springer-Verlag, Berlin, 1984.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, UCLA, 90024, Los Angeles, CA

    Michael G. Dyer

  2. Department of Computer Science and Engineering, Pohang Institute of Science and Technology, Korea

    Geunbae Lee

Authors
  1. Michael G. Dyer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Geunbae Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Dyer, M.G., Lee, G. Goal/plan analysis via distributed semantic representations in a connectionist system. Appl Intell 5, 165–197 (1995). https://doi.org/10.1007/BF00877230

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00877230

Keywords

Search

Navigation