Linguistic Relations Encoding in a Symbolic- Connectionist Hybrid Natural Language Processor
In recent years, the Natural Language Processing scene has witnessed the steady growth of interest in connectionist modeling. The main appeal of such an approach is that one does not have to determine the grammar rules in advance: the learning abilities displayed by such systems take care of input regularities. Better and faster learning can be obtained through the implementation of a symbolic-connectionist hybrid system. Such system combines the advantages of symbolic approaches, by introducing symbolic rules as network connection weights, with the advantages of connectionism. In a hybrid system called HTRP, words within a sentence are represented by means of semantic features. The features for the verbs are arranged along certain semantic dimensions, and are mutually exclusive within each dimension. One may infer that this happens because of the semantic features encoded in the network inputs.
Unable to display preview. Download preview PDF.
- 1.Dowty, D.: On the Semantic Content of the Notion of ‘Thematic Role’, in G. Chierchia, B. H. Partee, and R. Turner (Eds.), Properties, Types, and Meaning, vol. 2, Semantic Issues, Dordrecht: Kluwer (1989) 69–129Google Scholar
- 2.Franchi, C. and Cançado, M.: Thematic Hierarchy (in Portuguese), Unpublished paper, Unicamp/USP, UFMG, Brazil (1998)Google Scholar
- 4.Garcez, A. S. d’A., Zaverucha, G., and Carvalho, L. A. V.: Connectionist Inductive Learning and Logic Programming System, System Engineering and Computing Program —COPPE/UFRJ, Rio de Janeiro, Brazil, Technical Report (1997)Google Scholar
- 5.Haegeman, L.: Introduction to Government and Binding Theory. Cambridge: Blackwell (1991)Google Scholar
- 8.McClelland, J. L. and Kawamoto, A. H.: Mechanisms of Sentence Processing: Assigning Roles to Constituents of Sentences. In J. L. McClelland, D. E. Rumelhart (Eds.), Parallel Distributed Processing, Volume 2. A Bradford Book, The MIT Press (1986)Google Scholar
- 9.Rosa, J. L. G. and Françozo, E.: Hybrid Thematic Role Processor: Symbolic Linguistic Relations Revised by Connectionist Learning. Proceedings of IJCAI’99 — Sixteenth International Joint Conference on Artificial Intelligence, Volume 2, Stockholm, Sweden, 31 July-6 August, Morgan Kaufmann (1999) 852–857Google Scholar
- 10.Rosenblatt, F.: The Perceptron: A Perceiving and Recognizing Automaton, Report 85-460-1, Project PARA, Cornell Aeronautical Laboratory, Ithaca, New York (1957)Google Scholar
- 11.Rumelhart, D. E., Hinton, G. E., and Williams, R. J.: Learning Internal Representations by Error Propagation, in D. E. Rumelhart and J. L. McClelland (Eds.), Parallel Distributed Processing-Volume 1: Foundations, A Bradford Book, The MIT Press (1986)Google Scholar
- 12.Setiono, R. and Liu, H.: Symbolic Representation of Neural Networks, IEEE Computer, Vol. 29, No. 3 (1996) 71–77Google Scholar
- 13.Towell, G. G. and Shavlik, J. W.: Extracting Refined Rules from Knowledge-based Neural Networks, Machine Learning, 13 (1993) 71–101Google Scholar