Abstract
This paper describes evaluative work carried out with a connectionist model of semantic memory investigated by Rumelhart [1], and later by McClelland et al [2]. Two critical issues were investigated, the nature of the semantic associations learned by the model, and the ability of an adapted version of the model to simulate human priming data. Analysis of the correspondence between the semantic associations developed in the network and those expected from human data indicated two sources of concern. First, the semantic associations learned were susceptible to small changes in the training set. Second, surprising semantic relations were found (e.g. ‘animal’ was more similar to the plants in the model). Priming was studied by adding a cascade mechanism to the basic model. Certain aspects of the training data and model architecture made direct simulation of standard human semantic priming difficult, since primes and targets necessarily consisted of a concept and a relation term, e.g. prime ‘oak is’ — target ‘tree is’. Responses consisted of activation of appropriate features for the target term. Two interesting findings emerged. First, dissimilar primes slowed performance compared to unprimed processing. Second, the major causal factor in the priming effects obtained was due to the correspondence between relation terms rather than similarity of concepts. In light of these findings, we discuss the value, for connectionist modelling, of training data that encodes distribution information derived from the study of human semantic memory.
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
Rumelhart DE. Brain style computation:Learning and generalisation. In: SF. Zornetzer JL. Davis, and C.Lau. (eds) An introduction to neural and electronic networks. Academic Press: SanDiego, CA. 1990, pp 6–420.
McClelland JL., McNaughton BL., and O’Reilly R.C. Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory. Psychological Review 1995; 102(3): 419–457.
Plunkett K., Development in a connectionist framework: Rethinking the nature-nurture debate. The newsletter of the Center for Research in Language, 1996;10
Rumelhart DE. and Todd PM. Learning and connectionist representations. In DE. Meyer and S. Kornblum (eds) Attention and Performance XIV: Synergies in experimental psychology, artificial intelligence, and cognitive neuroscience. MIT Press, Cambridge, MA., 1992 pp 3–30.
Keil FC. Semantic and conceptual development: An ontological perspective. Harvard University Press, London, 1979.
Neely, JH.Semantic priming effects in visual word recognition: A selective review of current findings and theories. In: D. Besner and GW. Humphreys (eds) Basic processes in reading: Visual word recognition. Lawrence Erlbaum Associates, Hillsdale, NJ.,1991.
Collins, AM. and Loftus EF. A spreading activation theory of semantic processing. Psychological Review 1975; 82: 407–428.
Anderson JR The architecture of cognition. Harvard Press, Cambridge. MA, 1983
Ratcliff R. and McKoon G. A retrieval theory of priming in semantic memory. Psychological Review 1988; 95:385–408.
Farah, MJ. and McClelland JL. A computational model of semantic memory impairment:Modality specificity and emergent category specificity. Journal of Experimental Psychology:General 1991; 120: 339–357.
McRae K., de Sa VR. and Seidenberg MS. On the nature and scope of featural representations of word meaning. Journal of Experimental Psychology: General 1997; 126(2): 99–130.
Plaut DC. Semantic and associative priming in a distributed attractor network. In 17th Annual Conference of the Cognitive Science Society. Lawrence Erlbaum Associates. 1995.
Bullinaria JA. Modelling lexical decision: Who needs a lexicon? in Neural Computing Research and Applications III (Proceedings of the Fifth Irish Neural Networks Conference). Maynooth, Ireland: St. Patrick’s College, 1995.
Collins AM. and Quillian MR. Retrieval time from semantic memory. Journal of Verbal Learning and verbal behaviour 1969; 8: 240–247.
Hartley SJ. The development of conceptual knowledge: connectionist and experimental insights. PhD thesis, University of Sheffield, England, in preparation.
Cohen JD., McClelland JL. and Dunbar K. On the control of automatic processes: A parallel distributed procesing account of the stroop effect. Psychological Review 1990; 97(3): 332–361
Hinton GE. and Shallice T. Lesioning a connectionist network: Investigations of acquired dyslexia. Psychological Review 1991; 98: 74–95.
Bullinaria, JA. and Huckle CC. Modelling Lexical Decision using Corpus Derived Semantic Representations in a Connectionist Network. In: Fourth Neural Computation in Psychology Workshop. Springer Verlag, London, 1998.
Rips LJ., Shoben EJ. and Smith EE. Semantic distance and the verification of semantic relations. Journal of Verbal Learning and Verbal Behaviour 1973; 12:1–20.
Rosen, E. and Mervis CB. Family Resemblances: Studies in the internal structure of categories. Cognitive Psychology 1975; 7: 573–605.
Smith EE. and Medin DL. Categories and Concepts. Harvard University Press, Harvard, 1981.
Patel, M., Bullinaria, JA and Levy JP. Extracting Semantic Representations from Large Text Corpora. In Proceedings of the Fourth Neural Computation and Psychology Workshop. Springer Verlag, London, 1997
Hartley SJ., Prescott T.J. and Nicolson R.I. Experimental and Connectionist Perspectives on Semantic Memory Development. In MA. Gernsbacher and SJ. Derry (eds) Proceedings of the Twentieth Annual Conference of the Cognitive Science Society. Lawrence Erlbaum Ass, Mahwah, NJ, 1998 pp478–483.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Hartley, S.J., Prescott, T.J., Nicolson, R.I. (1999). Feature Distributions and Experimental Evaluation in a Connectionist Model of Semantic Memory. In: Heinke, D., Humphreys, G.W., Olson, A. (eds) Connectionist Models in Cognitive Neuroscience. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0813-9_14
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0813-9_14
Publisher Name: Springer, London
Print ISBN: 978-1-85233-052-1
Online ISBN: 978-1-4471-0813-9
eBook Packages: Springer Book Archive