Abstract
We propose a new method for developing distributed connectionist representations in order to serve as an adequate foundation for constructing and manipulating conceptual knowledge. In our approach, distributed representations of semantic relations (i.e. propositions) are formed by recirculating the hidden layer in two auto-associative recurrent PDP (parallel distributed processing) networks, and our experiments show that the resulting distributed semantic representations (DSRs) have many desirable properties such as automaticity, portability, structure-encoding ability and similarity-based distributed representations. We have constructed a symbolic/connectionist hybrid script-based story processing system dynasty (DYNAmic STory understanding sYstem) which incorporates DSR learning and 6 script related processing modules. Each module communicates through a global dictionary, where DSRs are stored, dynasty is able to (1) learn similarity-based distributed representations of concepts and events in everyday scriptal experiences, (2) perform script-based causal chain completion inferences according to the acquired sequential knowledge, and (3) perform script role association and retrieval during script application.
This research was supported in part by a contract from the JTF program of the DoD, monitored by JPL, and by an ITA Foundation Grant. The simulations were carried out on equipment awarded to the UCLA AI Laboratory by Hewlett Packard. Thanks to Risto Miikkulainen for providing a clustering code and to Trent Lange and John Reeves for proof reading a draft of this paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Allen, R.B. (1988) Sequential connectionist networks for answering simple questions about a microworld. In Proceedings of the Tenth Annual Cognitive Science Society Conference, pp. 489–495. Hillsdale, NJ: Erlbaum.
Bower, G.H., Black, J.B. & Turner, T.J. (1979) Scripts in memory for text. Cognitive Psychology, 11, 177–220.
Chalmers, D.J. (1990) Syntatic transformations on distributed representations. Connection Science, 2, 53–63.
Chun, H.W. & Mimo, A. (1987) A model of schema selection using marker passing and connectionist spreading activation. In Proceedings of the Ninth Annual Cognitive Science Society Conference, pp. 887–896. Hillsdale, NJ: Erlbaum.
Cullingford, R.E. (1978) Script application: computer understanding of newspaper stories. PhD thesis, Department of Computer Science, Yale University. Technical Report 116.
Dolan, C.P. (1989) Tensor manipulation networks: connectionist and symbolic approaches to comprehension, learning and planning. PhD thesis, Computer Science Department, UCLA.
Dolan, C.P. & Dyer, M.G. (1987) Symbolic schemata, role binding, and the evolution of structure in connectionist memories. In Proceedings of the IEEE First Annual International Conference on Neural Networks, Vol. 2, pp. 287–298. IEEE.
Dolan, C.P. & Smolensky, P. (1989) Implementing a connectionist production system using tensor products. In D. S. Touretzky, G. E. Hinton & T. J. Sejnowski (Eds) Proceedings of the 1988 Connectionist Models Summer School, pp. 265–272. Los Altos, CA: Morgan Kaufmann.
Dyer, M.G. (1990) Symbolic NeuroEngineering for natural language processing: a multilevel research approach. In J. Barnden & J. Pollack (Eds) Advances in Connectionist and Neural Computation Theory. Norwood, NJ: Ablex (in press).
Dyer, M.G., Cullingford, R.E. & Alvarado, S. (1987) Scripts. In S. C Shapiro (Ed.) Encyclopedia of Artificial Intelligence, pp. 980–994. New York: Wiley.
Dyer, M.G., Flowers, M. & Wang, A. (1988) Weight matrix = pattern of activation: encoding semantic networks as distributed representations in DUAL, a PDP architecture. Technical Report UCLA-AI-88-5, Artificial Intelligence Laboratory, Computer Science Department, University of California, Los Angeles.
Dyer, M.G., Flowers, M. & Wang, A. (1989) Distributed symbol discovery through symbol recirculation: toward natural language processing in distributed connectionist networks. In R. Reilly & N. Sharkey (Eds) Connectionist Approaches to Natural Language Understanding. Hillsdale, NJ: Erlbaum (in press).
Elman, J.L. (1988) Finding structure in time. Technical Report 8801, Center for Research in Language, University of California, San Diego.
Feldman, J.A. (1986) Neural representation of conceptual knowledge. Technical Report TR 189, Department of Computer Science, University of Rochester, NY.
Feldman, J.A. & Ballard, D.H. (1982) Connectionist models and their properties. Cognitive Science, 6, 205–254.
Fillmore, C.J. (1968) The case for case. In E. Bach & R. T. Harms (Eds) Universals in Linguistic Theory, pp. 1–90. New York: Holt, Rinehart & Winston.
Fodor, J. & Pylyshyn, Z. (1988) Connectionism and cognitive architecture: a critical analysis. Cognition, 28, 3–71.
Golden, R.M. (1986) Representing causal schemata in connectionist systems. In Proceedings of the Eighth Annual Cognitive Science Society Conference, pp. 13–22. Hillsdale, NJ: Erlbaum.
Hanson, S.J. & Kegl, J. (1987) Parsnip: a connectionist network that learns natural language grammar from exposure to natural language sentences. In Proceedings of the Ninth Annual Cognitive Science Society Conference, pp. 106–119. Hillsdale, NJ: Erlbaum.
Hartigan, J.A. (1975) Clustering Algorithms. New York: Wiley.
Hinton, G.E. (1986) Learning distributed representations of concepts. In Proceedings of the Eighth Annual Cognitive Science Society Conference, pp. 2–12. Hillsdale, NJ: Erlbaum.
Hinton, G.E. (1988) Representing part-whole hierarchies in connectionist networks. In Proceedings of the Tenth Annual Cognitive Science Society Conference, pp. 48–54. Hillsdale, NJ: Erlbaum.
Hinton, G.E., McClelland, J.L. & Rumelhart, D.E. (1986) Distributed representations. In D. E. Rumelhart & J. L. McClelland (Eds) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. I, Foundations, pp. 77–109. Cambridge, MA: MIT Press.
Lee, G. (1990a) Distributed semantic representations for goal/plan analysis of natural language stories in a connectionist architecture, PhD thesis, Computer Science Department, University of California, Los Angeles (in preparation).
Lee, G. (1990b) DYNASTYII: a neural network model of goal-based story processing system. Unpublished research report, Computer Science Department, UCLA.
Lee, G., Flowers, M. & Dyer, M.G. (1989a) Learning distributed representations of conceptual knowledge. Technical Report UCLA-AI-89-13, Artificial Intelligence Laboratory, Computer Science Department, University of California, Los Angeles.
Lee, G., Flowers, M. & Dyer, M.G. (1989b) A symbolic/connectionist script applier mechanism. In Proceedings of the Eleventh Annual Cognitive Science Society Conference, pp. 714–721. Hillsdale, NJ: Cognitive Science Society, Erlbaum.
McClelland, J.L. & Kawamoto, A.H. (1986) Mechanisms of sentence processing: assigning roles to constituents. In J. L. McClelland & D. E. Rumelhart (Eds) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. II, Psychological and Biological Models, pp. 272–326. Cambridge, MA: MIT Press.
Mead, C. (1987) Silicon models of neural computation. In Proceedings of the IEEE First Annual International Conference on Neural Networks. IEEE.
Miikkulainen, R. (1990) A distributed feature map model of the lexicon. Technical Report UCLA-AI-90-04, Artificial Intelligence Laboratory, Computer Science Department, University of California, Los Angeles.
Miikkulainen, R. & Dyer, M.G. (1988) Forming global representations with extended back-propagation. In Proceedings of the IEEE Second Annual International Conference on Neural Networks, Vol. 1, pp. 285–292. IEEE.
Miikkulainen, R. & Dyer, M.G. (1989) A modular neural network architecture for sequential paraphrasing of script-based stories. In Proceedings of the International Joint Conference on Neural Networks, Vol. 2, pp. 49–56. IEEE.
Pollack, J.B. (1988) Recursive auto-associative memory: devising compositional distributed representations. Technical Report MCCS-88-124, Computing Research Laboratory, New Mexico State University.
Pollack, J.B. (1990) Recursive distributed representations. Artificial Intelligence, 45, Special issue on connectionist symbol processing.
Rumelhart, D.E., Hinton, G.E. & Williams, R.J. (1986a) Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. I, Foundations, pp. 318–362. Cambridge, MA: MIT Press.
Rumelhart, D.E., McClelland, J.L. & the PDP Research Group (1986b) Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge, MA: MIT Press.
Rumelhart, D.E., Smolensky, P., McClelland, J.L. & Hinton, G.E. (1986c) Schemata and sequential thought processes in pdp models. In J. L. McClelland & D. E. Rumelhart (Eds) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. II, Psychological and Biological Models, pp. 7–57. Cambridge, MA: MIT Press.
Schank, R. (1973) Identification of conceptualization underlying natural language. In R. Schank & R. Colby (Eds) Computer Models of Thought and Language, pp. 187–248. San Francisco, CA: Freeman.
Schank, R. & Abelson, R. (1977) Scripts, Plans, Goals, and Understanding—an Inquiry into Human Knowledge Structures. The Artificial Intelligence Series. Hillsdale, NJ: Erlbaum.
Schank, R. & Riesbeck, C.K. (Eds) (1981) Inside Computer Understanding. Hillsdale, NJ: Erlbaum.
Smolensky, P. (1987a) A method for connectionist variable binding. Technical Report CU-CS-356-87, Department of Computer Science and Institute of Cognitive Science, University of Colorado, Boulder.
Smolensky, P. (1987b) On variable binding and the representation of symbolic structures in connectionist systems. Technical Report CU-CS-355-87, Department of Computer Science and Institute of Cognitive Science, University of Colorado, Boulder.
Smolensky, P. (1988) On the proper treatment of connectionism. Behavioral and Brain Sciences, 11, 1–74.
St John, M.F. & McClelland, J.L. (1989) Applying contextual constraints in sentence comprehension. In D. S. Touretzky, G. E. Hinton & T. J. Sejnowski (Eds) Proceedings of the 1988 Connectionist Models Summer School, pp. 338–346. Los Altos, CA: Morgan Kaufmann.
Touretzky, D.S. & Geva, S.A. (1988) A distributed connectionist representation for concept structures. In Proceedings of the Tenth Annual Cognitive Science Society Conference, pp. 155–163. Hillsdale, NJ: Erlbaum.
Touretzky, D.S. & Hinton, G.E. (1988) A distributed connectionist production system. Cognitive Science, 12, 423–436.
Waltz, D.L. & Pollack, J.B. (1985) Massively parallel parsing: a strongly interactive model of natural language interpretation. Cognitive Science, 9, 51–74.
Wilensky, R. (1978) Understanding goal-based stories. PhD thesis, Computer Science Department, Yale University.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Lee, G., Flowers, M., Dyer, M.G. (1992). Learning Distributed Representations of Conceptual Knowledge and their Application to Script-based Story Processing. In: Sharkey, N. (eds) Connectionist Natural Language Processing. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-2624-3_11
Download citation
DOI: https://doi.org/10.1007/978-94-011-2624-3_11
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-5160-6
Online ISBN: 978-94-011-2624-3
eBook Packages: Springer Book Archive