Abstract
A long-standing problem in the field of connectionist language processing has been how to represent detailed linguistic structure. Approaches have ranged from the encoding of syntactic trees in Raam to the use of a mechanism to query meanings in a “gestalt layer”. In this article, a technique called semantic self-organization is presented that allows for the optimal allocation and explicit representation of semantic dependency graphs on a Som-based grid. This technique has been successfully used in a connectionist natural language processing architecture called InSomNet to scale up the subsymbolic approach to represent sentences in the LinGO Redwoods HPSG Treebank drawn from the VerbMobil Project and annotated with rich semantic information. InSomNet was also shown to retain the cognitively plausible behavior detailed in psycholinguistics research. Consequently, semantic self-organization holds considerable promise as a basis for real-world natural language understanding systems that mimic human linguistic performance.
This is a preview of subscription content, log in via an institution to check access.
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
Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of English. Computational Linguistics 19, 313–330 (1993)
Oepen, S., Flickinger, D., Toutanova, K., Manning, C.: LinGO redwoods. In: Proceedings of the First Workshop on Treebanks and Linguistic Theories (TLT 2002), Sozopol, Bulgaria, TLT (2002)
Ruppenhofer, J., Ellsworth, M., Petruck, M.R.L., Johnson, C.R., Scheffczyk, J.: FrameNet II: Extended theory and practice. Technical report, ICSI (2005)
Mayberry, M.R., Miikkulainen, R.: Incremental nonmonotonic sentence processing through semantic self-organization. Cognitive Science (submitted)
Mayberry, M.R., Miikkulainen, R.: Incremental nonmonotonic parsing through semantic self-organization. In: Proceedings of the 25th Annual Conference of the Cognitive Science Society, pp. 367–372. Erlbaum, Mahwah (2003)
Mayberry, M.R.: Incremental Nonmonotonic Parsing through Semantic Self-Organization. PhD thesis, Department of Computer Sciences, The University of Texas at Austin, Austin, TX (2003)
Copestake, A., Flickinger, D., Sag, I.A., Pollard, C.: Minimal recursion semantics. Research on Language and Computation 3(2-3), 281–332 (2005)
Mayberry, M.R., Miikkulainen, R.: Using a sequential SOM to parse long-term dependencies. In: Proceedings of the 21st Annual Conference of the Cognitive Science Society, Hillsdale, NJ, pp. 367–372. Erlbaum, Mahwah (1999)
Toutanova, K., Manning, C.D., Shieber, S.M., Flickinger, D., Oepen, S.: Parse disambiguation for a rich HPSG grammar. In: First Workshop on Treebanks and Linguistic Theories (TLT2002), Sozopol, Bulgaria, pp. 253–263 (2002)
McClelland, J.L., Kawamoto, A.H.: Mechanisms of sentence processing. In: McClelland, J.L., Rumelhart, D.E. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Psychological and Biological Models, vol. 2, pp. 272–325. MIT Press, Cambridge (1986)
Miikkulainen, R.: Natural language processing with subsymbolic neural networks. In: Browne, A. (ed.) Neural Network Perspectives on Cognition and Adaptive Robotics, pp. 120–139. Institute of Physics Publishing, Bristol (1997)
Crocker, M.W., Keller, F.: Probabilistic grammars as models of gradience in language processing. In: Fanselow, G., Féry, C., Vogel, R., Schlesewsky, M. (eds.) Gradience in Grammar: Generative Perspectives, pp. 227–245. Oxford University Press, Oxford (2006)
Mitchell, D.C., Cuetos, F., Corley, M., Brysbaert, M.: Exposure-based models of human parsing. Journal of Psycholinguistic Research 24, 469–488 (1995)
Sperduti, A.: Encoding of Labeled Graphs by Labeling RAAM. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing Systems, vol. 7, pp. 1125–1132. MIT Press, Cambridge (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mayberry, M.R., Miikkulainen, R. (2009). Representing Semantic Graphs in a Self-Organizing Map. In: Príncipe, J.C., Miikkulainen, R. (eds) Advances in Self-Organizing Maps. WSOM 2009. Lecture Notes in Computer Science, vol 5629. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02397-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-02397-2_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02396-5
Online ISBN: 978-3-642-02397-2
eBook Packages: Computer ScienceComputer Science (R0)