Abstract
This paper describes a hybrid model which integrates symbolic and connectionist techniques for the analysis of noun phrases. Our model consists of three levels: (1) a distributed connectionist level, (2) a localist connectionist level, and (3) a symbolic level. While most current systems in natural language processing use techniques from only one of these three levels, our model takes advantage of the virtues of all three processing paradigms. The distributed connectionist level provides a learned semantic memory model. The localist connectionist level integrates semantic and syntactic constraints. The symbolic level is responsible for restricted syntactic analysis and concept extraction. We conclude that a hybrid model is potentially stronger than models that rely on only one processing paradigm.
We would like to thank Claire Cardie, David Lewis, Ellen Riloff, and the anonymous reviewers for comments on earlier drafts of this paper. This research was supported by the Advanced Research Projects Agency of the Department of Defense, monitored by the Office of Naval Research under contract No. N00014-87-K-0238, the Office of Naval Research, under a University Research Initiative Grant, Contract No. N00014-86-K-0764 and NSF Presidential Young Investigators Award NSFIST-8351863.
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. (1987) Several studies on natural language and back-propagation. Proceedings of the First Annual International Conference on Neural Networks.
Bookman, L.A. (1987) A microfeature based scheme for modelling semantics. Proceedings of the International Joint Conference on Artificial Intelligence.
Charniak, E. (1983) A parser with something for everyone. In M. King (Ed.) Parsing Natural Language. London: Academic Press.
Cosic, C. & Munro, P. (1988) Learning to represent and understand locative prepositional phrases. Proceedings of the Tenth Annual Conference of the Cognitive Science Society.
Cottrell, G.W. & Small, S.L. (1983) A connectionist scheme for modelling word sense disambiguation. Cognition and Brain Theory, 6.
Cottrell, G.W. (1988) A model of lexical access of ambiguous words. In S. I. Small, G. W. Cottrell & M. K. Tanenhaus (Eds) Lexical Ambiguity Resolution. San Mateo, CA: Morgan Kaufmann.
Crain, S. & Steedman, M. (1985) On not being led up the garden path: the use of context by the psychological syntax processor. In D. R. Dowty, L. Karttunen & A. M. Zwicky (Eds) Natural Language Parsing: Psychological, Computational, and Theoretical Perspectives. Cambridge: Cambridge University Press.
Dahlgren, K. (1988) Naive Semantics for Natural Language Understanding. Dordrecht: Kluwer.
Dahlgren, K. & McDowell, J. (1986) Using commonsense knowledge to disambiguate prepositional phrase modifiers. Proceedings of the National Conference on Artificial Intelligence.
Derthick, M. (1988) Mundane reasoning by parallel constraint satisfaction, Technical Report CMU-CS-88-182. Carnegie-Mellon University.
Dolan, C.P. & Dyer, M.G. (1988) Parallel retrieval and application of conceptual knowlege, Technical Report UCLA-AI-88-3. Los Angeles, CA: University of California.
Dyer, M.G. (1983) In-depth Understanding. Cambridge, MA: MIT Press.
Dyer, M.G. (1988) 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 Publishers (in press) (also available as Technical Report UCLA-AI-88-14, University of California, Los Angeles).
EJC (1967) Thesaurus of Engineering and Scientific Terms. New York: Engineers Joint Council.
Elman, J.L. (1988) Finding structure in time, Technical Report CRL-8801. San Diego, CA: University of California.
Fanty, M. (1985) Context-free parsing in connectionist networks, Technical Report 174. Rochester, NY: University of Rochester.
Feldman, J.A. & Ballard, D.H. (1982) Connectionist models and their properties. Cognitive Science, 6.
Ford, M., Bresnan, J.W. & Kaplan, R.M. (1982) A competence based theory of syntactic closure. In J. W. Bresnan (Ed.) The Mental Representation of Grammatical Relations. Cambridge, MA: MIT Press.
Frazier, L. & Fodor, J.D. (1978) The sausage machine: a new two-stage parsing model. Cognition, 6.
Gasser, M.E. (1988) A connectionist model of sentence generation in a first and second language, Technical Report UCLA-AI-88-13. Los Angeles, CA: University of California.
Grosz, B.J., Appelt, D.E., Martin, P.A. & Pereira, F.C.N. (1987) TEAM: an experiment in the design of transportable natural-language interfaces. Artificial Intelligence, 32.
Hanson, S.J. & Kegl, J. (1987) PARSNIP: a connectionist network that learns natural language grammar from exposure to natural language sentences. Proceedings of the Ninth Annual Conference of the Cognitive Science Society.
Hendler, J.A. (1989) Marker passing over microfeatures: towards a hybrid symbolic/connectionist model. Cognitive Science, 13.
Hinton, G.E. (1986) Learning distributed representations of concepts. Proceedings of the Eighth Annual Conference of the Cognitive Science Society.
Hinton, G.E. (1988) Representing part-whole hierarchies in connectionist networks. Proceedings of the Tenth Annual Conference of the Cognitive Science Society.
Hirschman, L. (1986) Discovering sublanguage structures. In R. Grishman & R. Kittredge (Eds) Analyzing Language in Restricted Domains: Sublanguage Description and Processing.
Hirst, G. (1987) Semantic Interpretation and the Resolution of Ambiguity. Cambridge: Cambridge University Press.
Howells, T. (1988) VITAL—A connectionist parser. Proceedings of the Tenth Annual Conference of the Cognitive Science Society.
Jensen, K. & Binot, J.L. (1987) Disambiguating prepositional phrase attachments by using on-line dictionary definitions. Computational Linguistics, 13.
Jordan, M.I. (1986) Attractor dynamics and parallelism in a connectionist sequential machine. Proceedings of the Eighth Annual Conference of the Cognitive Science Society.
Kimball, J. (1973) Seven principles of surface structure parsing in natural language. Cognition, 2.
Kwasny, S.C. (1988) A parallel distributed approach to parsing natural language deterministically, Technical Report WUCS-88-21. St Louis, WA: Washington University.
Lehnert, W.G. (1987) Learning to integrate syntax and semantics. Proceedings of the Fourth International Workshop on Machine Learning.
Lehnert, W.G. (1988) Symbolic/subsymbolic sentence analysis: exploiting the best of two worlds. In J. Barnden & J. Pollack (Eds) Advances in Connectionist and Neural Computation Theory. Norwood, NJ: Ablex (in press) (also available as COINS Technical Report 88–99, Department of Computer and Information Science, University of Massachusetts, Amherst, MA).
NASA (1985) NASA Thesaurus (National Aeronautics and Space Administration).
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, Vol. 2. Cambridge, MA: MIT Press.
Miikulainen, R. & Dyer, M.G. (1989) A modular neural network architecture for sequential paraphrasing of script-based stories, Technical Report UCLA-AI-89-02. Los Angeles, CA: University of California.
Pollack, J. (1988) Recursive auto-associative memory: devising compositional distributed representations. Proceedings of the Tenth Annual Conference of the Cognitive Science Society.
Pollack, J. (1989) Implications of recursive distributed representations. Conference on Neural Information Processing Systems (submitted).
Riesbeck, C. & Martin, C. (1986) Direct memory access parsing. In C. Riesbeck & J. Kolodner (Eds) Experience, Memory and Reasoning. Hillsdale, NJ: Lawrence Erlbaum.
Rumelhart, D.E., Hinton, G.E. & Williams, R.J. (1986) Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds) Parallel Distributed Processing, Vol. 1. Cambridge, MA: MIT Press.
Rumelhart, D.E. & McClelland, J.L. (1986) On learning the past tenses of English verbs. In J. L. McClelland & D. E. Rumelhart (Eds) Parallel Distributed Processing, Vol. 2. Cambridge, MA: MIT Press.
Schank, R.D. & Riesbeck, C. (1981) Inside Computer Understanding. Hillsdale, NJ: Lawrence Erlbaum.
Schubert, L.K. (1986) Are there preference tradeoffs in attachment decisions? Proceedings of the National Conference on Artificial Intelligence.
Sejnowski, T.J. & Rosenberg, C.R. (1986) NETtalk: a parallel network that learns to read aloud, Technical Report JHU/EECS-86/01. Baltimore, MD: Johns Hopkins University Press.
Shastri, L. (1988) A connectionist approach to knowledge representation and limited inference. Cognitive Science, 12.
Shastri, L. & Ajjanagadde, V. (1989) A connectionist system for rule based reasoning with multi-place predicates and variables, Technical Report MS-CIS-89-06. University of Pennsylvania.
Sparck Jones, K. & Rijsbergen, C.J. (1976) Information retrieval test collections. Journal of Documentation, 32.
St John, M.F. & McClelland, J.L. (1988) Applying contextual constraints in sentence comprehension. Proceedings of the Tenth Annual Conference of the Cognitive Science Society.
Tait, J.I. (1983) Semantic parsing and syntactic constraints (Mark IV). In K. Sparck Jones & Y. Wilks (Eds) Automated natural language processing. Chichester: Ellis Horwood.
Touretzky, D.S. (1988) Beyond associative memory: connectionists must search for other cognitive primitives. Proceedings of the AAAI Spring Symposium Series: Parallel Models of Intelligence: How Can Slow Components Think so Fast?
Touretzky, D.S. (1989) Connectionism and compositional semantics, Technical Report CMU-CS-89-147. Carnegie Mellon University.
Touretzky, D.S. & Hinton, G.E. (1985) Symbols among the neurons: details of a connectionist inference architecture. Proceedings of the International Joint Conference on Artificial Intelligence.
Touretzky, D.S. & Hinton, G.E. (1988) A distributed connectionist production system. Cognitive Science, 12.
Waltz, D.L. & Pollack, J.B. (1985) Massively parallel parsing: a strongly interactive model of natural language interpretation. Cognitive Science, 9.
Wermter, S. (1989a) Integration of semantic and syntactic constraints for structural noun phrase disambiguation. Proceedings of the International Joint Conference on Artificial Intelligence.
Wermter, S. (1989b) Learning semantic relationships in compound nouns with connectionist networks. Proceedings of the Eleventh Annual Conference of the Cognitive Science Society.
Wilks, Y., Huang, X. & Fass, D. (1985) Syntax, preference and right attachment. Proceedings of the International Joint Conference on Artificial Intelligence.
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
Wermter, S., Lehnert, W.G. (1992). A Hybrid Symbolic/Connectionist Model for Noun Phrase Understanding. In: Sharkey, N. (eds) Connectionist Natural Language Processing. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-2624-3_6
Download citation
DOI: https://doi.org/10.1007/978-94-011-2624-3_6
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-5160-6
Online ISBN: 978-94-011-2624-3
eBook Packages: Springer Book Archive