Skip to main content
Log in

Connectionist representation, semantic compositionality, and the instability of concept structure

  • Published:
Psychological Research Aims and scope Submit manuscript

Summary

In the present paper connectionist approaches to the problem of internal representation and the nature of concepts are discussed. In the first part the concept of representation that underlies connectionist modeling is made explicit. It is argued that the connectionist view of representation relies on a correlational theory of semantic content- i.e., the covariation between internal and external states is taken as the basis for ascribing meaning to internal states. The problems and virtues of such a correlational approach to internal representation are addressed. The second part of the paper is concerned with whether connectionism is capable of accounting for the apparent productivity and systematicity of language and thought. There is an evaluation of the recent arguments of Fodor and Pylyshyn, who claim that systematicity can only be explained if one conceives of mental representations as structured symbols composed of context-free constituents. There is a review of empirical evidence that strongly suggests that concepts are not fixed memory structures and that the meaning of constituent symbols varies, depending on the context in which they are embedded. On the basis of this review it is concluded that the meaning of a complex expression is not computed from the context-free meanings of the constituents, and that strong compositionality, as endorsed by Fodor and Pylyshyn (1988), seems implausible as a process theory for the comprehension of complex concepts. Instead, the hypothesis is endorsed that constraint satisfaction in distributed connectionist networks may allow for an alternative account of weak compositionality compatible with the context sensitivity of meaning. In the final section, it is argued that neither mere implementation of a “language of thought” in connectionist networks nor radical elimination of symbol systems seems to be a fruitful research strategy, but that it might be more useful to discuss how connectionist systems can develop the capacity to use external symbol systems like language or logic without instantiating symbol systems themselves.

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

Access this article

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

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Barclay, J. R., Bransford, J. D., Franks, J. J., McCarrell, N. S., & Nitsch, K. (1974). Comprehension and semantic flexibility.Journal of Verbal Learning and Verbal Behavior, 13, 471–481.

    Google Scholar 

  • Barsalou, L. W. (1982). Context-independent and context-dependent information in concepts.Memory & Cognition, 10, 82–93.

    Google Scholar 

  • Barsalou, L. W. (1987). The instability of graded structure: Implications for the nature of concepts. In U. Neisser (Ed.),Concepts and conceptual development: Ecological and intellectual factors in categorization. Cambridge: Cambridge University Press.

    Google Scholar 

  • Barsalou, L. W. (1989). Intraconcept similarity and its implications for interconcept similarity. In S. Vosniadou & A. Ortony, (Eds.),Similarity and analogical reasoning, (pp. 76–121). Cambridge: Cambridge University Press.

    Google Scholar 

  • Bechtel, W. (1990). Multiple levels of inquiry in cognitive science.Psychological Research, 52, 271–281.

    Google Scholar 

  • Bechtel, W., & Abrahamsen, A. A. (1990).Connectionism and the mind: An introduction to parallel processing in networks. Oxford: Basil Blackwell.

    Google Scholar 

  • Block, N. (1986). Advertisment for a semantics for psychology.Midwest Studies in Philosophy, 10, 615–678.

    Google Scholar 

  • Brousse, O., & Smolensky, P. (1990). Connectionist generalization and incremental learning in combinatorial domains. In H. Haken & M. Stadler (Eds.),Synergetics of cognition. Berlin, Heidelberg, New York: Springer.

    Google Scholar 

  • Churchland, P. M. (1989).A neurocomputational perspective: The nature of mind and the structure of science. Cambridge, MA: MIT Press.

    Google Scholar 

  • Churchland, P. M., & Churchland, P. S. (1983). Content: Semantic and information-theoretic.Behavioral and Brain Sciences, 6, 67.

    Google Scholar 

  • Clark, A. (1989).Microcognition: Philosophy, cognitive science, and parallel distributed processing. Cambridge, MA: MIT Press.

    Google Scholar 

  • Clark, H. H. (1969). Linguistic processes in deductive reasoning.Psychological Review, 76, 387–404.

    Google Scholar 

  • Clark, H. H. (1983). Making sense of nonce sense. In G. Flores D'Arcais & R. J. Jarvella (Eds.),The process of language understanding. Chichester: Wiley.

    Google Scholar 

  • Collins, A. M., & Quillian, M. R. (1969). Retrieval time from semantic memory.Journal of Verbal Learning and Verbal Behavior, 8, 240–247.

    Google Scholar 

  • Cummins, R. (1989).Meaning and mental representation. Cambridge, MA: MIT Press.

    Google Scholar 

  • Dennett, D. C. (1987).The intentional stance. Cambridge, MA: MIT Press.

    Google Scholar 

  • Dretske, F. I. (1981).Knowledge and the flow of information. Cambridge, MA: MIT Press.

    Google Scholar 

  • Dretske, F. I. (1983). Précis of knowledge and the flow of information.Behavioral and Brain Sciences, 6, 55–90.

    Google Scholar 

  • Dretske, F. I. (1988).Explaning behavior. Reasons in a world of causes. Cambridge, MA: MIT Press.

    Google Scholar 

  • Elman, J. L. (1989).Representation and structure in connectionist models. CRL Technical Report 8903, Center for Research in Language, University of California, San Diego.

    Google Scholar 

  • Elman, J. L., & Zipser, D. (1987).Learning the hidden structure of speech. Technical Report 8701, Institute for Cognitive Science, University of California, San Diego.

    Google Scholar 

  • Evans, J. St. B. T. (1982).The psychology of deductive reasoning. London: Routledge and Kegan Paul.

    Google Scholar 

  • Feldman, J. A., & Ballard, D. H. (1982). Connectionist models and their properties.Cognitive Science, 6, 205–254.

    Google Scholar 

  • Fodor J. A. (1983).The modularity of mind. Cambridge, MA: MIT Press.

    Google Scholar 

  • Fodor J. A. (1984). Semantics, Wisconsin style.Synthese, 59, 231 -250.

    Google Scholar 

  • Fodor J. A. (1987).Psyehosemantics. The problem of meaning in the philosophy of mind. Cambridge, MA: MIT Press.

    Google Scholar 

  • Fodor J. A., & McLaughlin, B. (1990). Connectionism and the problem of systematicity: Why Smolensky's solution doesn't work.Cognition, 35, 183–204.

    PubMed  Google Scholar 

  • Fodor J. A., & Pylyshyn, Z. W. (1988). Connectionism and cognitive architecture: A critical analysis.Cognition, 28, 3–71.

    PubMed  Google Scholar 

  • Frauenfelder, U. H., & Tyler, L. K. (1987). The process of spoken word recognition: An introduction.Cognition, 25, 1–20.

    PubMed  Google Scholar 

  • Fuchs, A., Goschke, T., & Gude, D. (1988). On the role of imagery in linear syllogistic reasoning.Psychological Research, 50, 43–49.

    Google Scholar 

  • Galotti, K. M. (1989). Approaches to studying formal and everyday reasoning.Psychological Bulletin, 105, 331–351.

    Google Scholar 

  • Gelder, T. J. van (1988).Connectionist representations: Combinatorial, compostional, or neither? Department of Philosophy, University of Pittsburgh, Pittsburgh.

    Google Scholar 

  • Goschke, T. (1989). Implikationen des Neuen Konnektionismus für den Begriff der mentalen Repräsentation. In B. Becker (Ed.),Zur Terminologie der Kognitionsforschung. Sankt Augustin: Gesellschaft für Mathematik und Datenverarbeitung.

    Google Scholar 

  • Goschke, T., & Koppelberg, D. (1990). The concept of representation and the representation of concepts in connectionist models. In W. Ramsey, D. E. Rumelhart, & S. Stich (Eds.),Philosophy and connectionist theory. Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Greenspan, S. L. (1986). Semantic flexibility and referential specificity of concrete nouns.Journal of Memory and Language, 25, 539–557.

    Google Scholar 

  • Grice, P (1957). Meaning.Philosophical Review, 66, 377–388.

    Google Scholar 

  • Hampton, J. A. (1987). Inheritance of attributes in natural concept conjunctions.Memory & Cognition, 15, 55–71.

    Google Scholar 

  • Hampton, J. A. (1988). Overextension of conjunctive concepts: Evidence for a unitary model of concept typicality and class inclusion.Journal of Experimental Psychology: Learning, Memory, and Cognition, 14, 12–32.

    Google Scholar 

  • Hebb, D. O. (1949).The organization of behavior. New York: Wiley.

    Google Scholar 

  • Hinton, G. E. (1986). Learning distributed representations of concepts.Proceedings of the 8th Annual Conference of the Cognitive Science Society. Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Hinton, G. E. (1987).Connectionist learning procedures. Technical Report CMU-CS-87-115. Computer Science Department, CarnegieMellon University, Pittsburgh, PA.

    Google Scholar 

  • Hinton, G. E., & Anderson, J. A. (1981) (Eds.).Parallel Models of Associative Memory. Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • 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. 1, pp. 77–109). Cambridge, MA: MIT Press.

    Google Scholar 

  • Hintzman, D. L. (1990). Human learning and memory: Connections and dissociations.Annual Review of Psychology, 41, 109–139.

    PubMed  Google Scholar 

  • Hörmann, H. (1976).Meinen und Verstehen. Frankfurt a.M.: Suhrkamp.

    Google Scholar 

  • Hörmann, H. (1983).Was tun die Wörter miteinander im Satz? oder Wieviele sind einige, mehrere und ein paar? Göttingen: Hogrefe.

    Google Scholar 

  • Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, USA, 79, 2554–2558.

    Google Scholar 

  • Huttenlocher, J. (1968). Constructing spatial images: A strategy in reasoning.Psychological Review, 75, 550–560.

    Google Scholar 

  • Jordan, M. I. (1986). Attractor dynamics and parallelism in a connectionist sequential machine.Proceedings of the 8th Annual Conference of the Cognitive Science Society. Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Kahneman, D., & Miller, D. T. (1986). Norm theory: Comparing reality to its alternatives.Psychological Review, 93, 136–153.

    Google Scholar 

  • Klix, F. (1983). An evolutionary approach to cognitive processes and creativity in human being. In R. Groner, M. Groner, & W. F. Bischof (Eds.),Methods of heuristics. Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Lachter, J., & Bever, T. G. (1988). The relation between linguistic structure and associative theories of language learning — A constructive critique of some connectionist learning models.Cognition, 28, 195–247.

    PubMed  Google Scholar 

  • Lahav, R. (1989). Against compositionality: The case of adjectives.Philosophical Studies, 57, 261–279.

    Google Scholar 

  • Levelt, W. J. M. (1990). Are multilayer feedforward networks effectively turing machines?Psychological Research, 52, 153–157.

    Google Scholar 

  • Lloyd, D. (1989).Simple minds. Cambridge, MA: MIT Press.

    Google Scholar 

  • Margolis, H. (1987).Patterns, thinking, and cognition. Chicago: University of Chicago Press.

    Google Scholar 

  • Marslen-Wilson, W. (1987). Functional parallelism in spoken word-recognition.Cognition, 25, 71–102.

    PubMed  Google Scholar 

  • Marslen-Wilson, W., & Tyler, L. K. (1980). The temporal structure of spoken language understanding.Cognition, 8, 1–71.

    PubMed  Google Scholar 

  • Marslen-Wilson, W., & Tyler, L. K. (1987). Against modularity. In J. L. Garfield (Ed.),Modularity in knowledge representation and language comprehension. Cambridge, MA: MIT Press.

    Google Scholar 

  • Maybery, M. T., Bain, J. D., & Halford, G. S. (1986). Information-processing demands of transitive inference.Journal of Experimental Psychology: Learning, Memory, and Cognition, 12, 600–613.

    Google Scholar 

  • McClelland, J. L., & Kawamoto, A. H. (1986). Mechanisms of sentence processing: Assigning roles to constituents. In J. L. McClelland, D. E. Rumelhart, & The PDP Research Group (Eds.),Parallel Distributed Processing. Explorations in the Microstructure of Cognition (Vol. 2, pp. 272–326). Cambridge, MA: MIT Press.

    Google Scholar 

  • McClelland, J. L., & Rumelhart, D. E. (1981). An interactive activation model of context effects in letter perception: Part I. An account of basis findings.Psychological Review, 88, 375–407.

    Google Scholar 

  • McClelland, J. L., & Rumelhart, D. E., & The PDP Research Group (1986).Parallel Distributed Processing. Explorations in the Microstructure of Cognition (Vol. 2). Cambridge, MA: MIT Press.

    Google Scholar 

  • McCloskey, M., & Glucksberg, S. (1978). Natural categories: Welldefined or fuzzy sets?Memory & Cognition, 6, 462–472.

    Google Scholar 

  • McGinn, C. (1982). The structure of content. In A. Woodfield (Ed.),Thought and object. Oxford: Oxford University Press.

    Google Scholar 

  • Medin, D. L., & Ortony, A. (1989). Psychological essenfalism. In S. Vosniadou & A. Ortony (Eds.),Similarity and analogical reasoning (pp. 179–196). Cambridge: Cambridge University Press.

    Google Scholar 

  • Medin, D. L., & Shoben, E. J. (1988). Context and structure in conceptual combination.Cognitive Psychology, 20, 158–190.

    PubMed  Google Scholar 

  • Millikan, R. G. (1986). Thoughts without laws, cognitive science with content.Philosophical Review, 95, 47–81.

    Google Scholar 

  • Minsky, M., & Papert, S. (1969).Perceptrons. Cambridge, MA: MIT Press.

    Google Scholar 

  • Murphy, G. L. (1988). Comprehending complex concepts.Cognitive Science, 12, 529–562.

    Article  Google Scholar 

  • Osherson, D. N., & Smith, E. E. (1981). On the adequacy of prototype theory as a theory of concepts.Cognition, 9, 35–58.

    PubMed  Google Scholar 

  • Partee, B. H. (1984). Compositionality. In F. Landman & F. Veltman (Eds.),Varieties of formal semantics. Dordrecht: Foris.

    Google Scholar 

  • Ramsey, W., Stich, S., & Garon, J. (1990). Connectionism, eliminativism, and the future of folk psychology. In W. Ramsey, D. E. Rumelhart, & S. Stich (Eds.),Philosophy and connectionist theory. Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Rey, G. (1983). Concepts and stereotypes.Cognition, 15, 237–262.

    PubMed  Google Scholar 

  • Richardson-Klavehn, A., & Bjork, R. A. (1988). Measures of memory.Annual Review of Psychology, 39, 475–543.

    Google Scholar 

  • Rips, L. J., Shoben, E. J., & Smith, E. E. (1973). Semantic distance and the verification of semantic relations.Journal of Verbal Learning and Verbal Behavior, 12, 1–20.

    Google Scholar 

  • Rosch, E. (1973). On the internal structure of perceptual and semantic categories. In T. E. Moore (Ed.),Cognitive development and the acquisition of language. New York: Academic Press.

    Google Scholar 

  • Rosch, E. (1975). Cognitive representation of semantic categories.Journal of Experimental Psychology: General, 104, 192–233.

    Google Scholar 

  • Rosenberg, J. F. (1989). Connectionism and cognition. Report 1/1989. Research Group on "Mind and Brain," Center of Interdisciplinary Research (ZIF), University of Bielefeld, Bielefeld.

    Google Scholar 

  • Rosenblatt, F. (1962).Principles of neurodynamics. New York: Spartan Books.

    Google Scholar 

  • Roth, E. M., & Shoben, E. J. (1983). The effect of context on the structure of categories.Cognitive Psychology, 15, 346–378.

    Google Scholar 

  • Rumelhart, D. E. (1979). Some problems with the notion of literal meaning. In A. Ortony (Ed.),Metaphor and thought. Cambridge: Cambridge University Press.

    Google Scholar 

  • Rumelhart, D. E., & Zipser, D. (1986). Feature discovery by competitive learning. In D. E. Rumelhart, J. L. McClelland, & The PDP Research Group (1986).Parallel distributed processing. Explorations in the microstructure of cognition (Vol. 1). Cambridge, MA: MIT Press.

    Google Scholar 

  • Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning internal representations by back-propagating errors.Nature, 323, 533–536.

    Google Scholar 

  • Rumelhart, D. E., McClelland, J. L., & The PDP Research Group (1986).Parallel distributed processing. Explorations in the microstructure of cognition (Vol. 1). Cambridge, MA: MIT Press.

    Google Scholar 

  • Rumelhart, D. E., Smolensky, P., McClelland, J. L., & Hinton, G. E. (1986). Schemata and sequential thought processes in PDP models. In J. L. McClelland, D. E. Rumelhart, & The PDP Research Group (1986).Parallel distributed processing. Explorations in the microstructure of cognition (Vol. 2). Cambridge, MA: MIT Press.

    Google Scholar 

  • Ryle, G. (1949).The concept of mind. Harmondsworth: Penguin Books.

    Google Scholar 

  • Sanger, D. (1989). Contribution analysis: A technique for assigning responsibilities to hidden units in connectionist networks. Technical Report CU-CS-435-89, Department of Computer Science, University of Colorado, Boulder.

    Google Scholar 

  • Schacter, D. L. (1987). Implicit memory: History and current status.Journal of Experimental Psychology: Learning, Memory, and Cognition, 13, 501–518.

    Google Scholar 

  • Scheerer, E. (1989). Symbolverarbeitung und Konnektionismus: Eine Kontroverse ohne Ende? In B. Becker (Ed.), Zur Terminologie der Kognitionsforschung. Arbeitsberichte der GMD. Birlinghoven: Gesellschaft füir Mathematik und Datenverarbeitung.

    Google Scholar 

  • Schiffer, S. (1987).Remnants of meaning. Cambridge, MA: MIT Press.

    Google Scholar 

  • Seidenberg, M. S. (1985). Constraining models of word recognition.Cognition, 14, 169–190.

    Google Scholar 

  • Seidenberg, M. S., & Tanenhaus, M. K., Leiman, J. M., & Bienkowski, M. (1982). Automatic access of the meanings of ambiguous words in context: Some limitations of knowledge-based processing.Cognitive Psychology, 14, 489–537.

    Article  Google Scholar 

  • Sellars, W. (1981). Mental events.Philosophical Studies, 39, 325–345.

    Google Scholar 

  • Servan-Schreiber, D., Cleeremans, A., & McClelland, J. L. (1988).Encoding sequential structure in simple recurrent networks. Technical Report CMU-CS-88-183. School of Computer Science, Carnegie Mellon University, Pittsburgh.

    Google Scholar 

  • Sejnowski, T. J., & Rosenberg, C. R. (1987). Parallel networks that learn to pronounce English text.Complex Systems, 1, 145–168.

    Google Scholar 

  • Shastri, L., & Feldman, J. A. (1986). Neural nets, routines and semantic networks. In N. E. Sharkey (Ed.),Advances in cognitive science (Vol. 1). Chichester: Ellis Norwood.

    Google Scholar 

  • Shaver, P., Pierson, L., & Lang, S. (1974-5). Converging evidence for the functional significance of imagery in problem solving.Cognition, 3, 359–375.

    Google Scholar 

  • Sherry, D. E., & Schacter, D. L. (1987). The evolution of multiple memory systems.Psychological Review, 94, 439–454.

    Google Scholar 

  • Smith, E. E. (1987). Concepts and thought. In R. J. Sternberg & E. E. Smith (Eds.),The psychology of human thought. Cambridge, MA: Cambridge University Press.

    Google Scholar 

  • Smith, E. E., & Medin, D. (1981).Categories and concepts. Cambridge, MA: Harvard Univeristy Press.

    Google Scholar 

  • Smith, E. E., & Osherson, D. N. (1984). Conceptual combination with prototype concepts.Cognitive Science, 8, 337–361.

    Google Scholar 

  • Smith, E. E., Shoben, E. J., & Rips, L. J. (1974). Structure and process in semantic memory: A featural model for semantic decisions.Psychological Review, 81, 214–241.

    Google Scholar 

  • Smith, E. E., & Osherson, D. N., Rips, L. J., & Keane, M. (1988). Combining concepts: A selective modification model.Cognitive Science, 12, 485–527.

    Google Scholar 

  • Smolensky, P. (1986). Formal modeling of subsymbolic processes: An introduction to harmony theory. In N. E. Sharkey (Ed.),Advances in cognitive science (Vol. 1). Chichester: Ellis Norwood.

    Google Scholar 

  • Smolensky, P. (1987).A method for connectionist variable binding. Technical Report CU-CS-356-87. Department of Computer Science, University of Colorado, Boulder.

    Google Scholar 

  • Smolensky, P. (1988). On the proper treatment of connectionism.Behavioral and Brain Sciences, 11, 1–74.

    Google Scholar 

  • Stich, S. P. (1988). From connectionism to eliminativism.Behavioral and Brain Sciences, 11, 53.

    Google Scholar 

  • St. John, M., & McClelland, J. L. (1988). Applying contextual constraints in sentence comprehension.Proceedings of the 10th Annual Conference of the Cognitive Science Society (pp. 26–32). Hillsdale: Erlbaum.

    Google Scholar 

  • Strube, G. (1984).Assoziation. Berlin, Heidelberg, New York: Springer.

    Google Scholar 

  • Strube, G. (1990). Neokonnektionismus: Fine neue Basis für die Theorie und Modellierung menschlicher Kognition?Psychologische Rundschau, 41, 129–143.

    Google Scholar 

  • Strube, G., Hemforth, B., & Wrobel, H. (1989). Auf dem Weg zu psychologisch fundierten Modellen menschlicher Sprachverarbeitung: Echtzeitanalysen des Satzverstehens. Manuscript, Ruhr-Universität Bochum.

  • Swinney, D. A. (1979). Lexical access during sentence comprehension: (Re)consideration of context effects.Journal of Verbal Learning and Verbal Behavior, 6, 645–659.

    Google Scholar 

  • Tabossi, P. (1988). Effects of context on the immediate interpretation of unambiguous nouns.Journal of Experimental Psychology: Learning, Memory, and Cognition, 14, 153–162.

    Google Scholar 

  • Tabossi, P. (1989). What's in a context? In D. S. Gorfein (Ed.),Resolving semantic ambiguity (pp. 25–39). New York, Berlin, Heidelberg: Springer.

    Google Scholar 

  • Tanenhaus, M. K., & Lucas, M. M. (1987). Context effects in lexical processing.Cognition, 25, 213–234.

    PubMed  Google Scholar 

  • Thagard, P. (1989). Explanatory coherence.Behavioral and Brain Sciences, 12, 435–502.

    Google Scholar 

  • Touretzky, D. S., & Hinton, G. E. (1988). A distributed connectionist production system.Cognitive Science, 12, 423–466.

    Google Scholar 

  • Vygotski, L. S. (1962).Thought and language. Cambridge, MA: MIT Press.

    Google Scholar 

  • Walker, W. H., & Kintsch, W. (1985). Automatic and strategic aspects of knowledge retrieval.Cognitive Science, 9, 261–283.

    Google Scholar 

  • Waltz, D. L., & Pollack, J. B. (1985). Massively parallel parsing: A strongly interactive model of natural language interpretation.Cognitive Science, 9, 51–74.

    Google Scholar 

  • Whitney, P., McKay, T., & Kellas, G. (1985). Semantic activation of noun concepts in context.Journal of Experimental Psychology: Learning, Memory, and Cognition, 11, 126–135.

    Google Scholar 

  • Ziff, P. (1960).Semantic Analysis. Ithaca: Cornell University Press.

    Google Scholar 

  • Zwitserlood, P. (1989). The locus of the effects of sentential-semantic context in spoken-word processing.Cognition, 32, 25–64.

    PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Goschke, T., Koppelberg, D. Connectionist representation, semantic compositionality, and the instability of concept structure. Psychol. Res 52, 253–270 (1990). https://doi.org/10.1007/BF00877534

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00877534

Keywords

Navigation