A connectionist parser for context-free phrase structure grammars
Most connectionist networks in present use employ built-in learning algorithms. Their major disadvantage however is their inability to handle complex knowledge structures. In this paper a connectionist network is presented which can handle highly developed cognitive structures not by making use of learning processes but by the integration of a powerful initial structure. Parsing of context-free phrase structure grammars shall exemplify the workings of the network.
Unable to display preview. Download preview PDF.
- Feldman, J.A. (1988) “Structured neural networks in nature and in computer science.” In: Eckmiller, R. & v.d.Malsburg, Chr. Neural Computers, Berlin etc.: Springer.Google Scholar
- Hoelter, M. (1990) “Net-linguistic representation of complex feature structures”. unpublished Ms. Ruhr-Universität BochumGoogle Scholar
- Schnelle, H. & Doust, R. (1989) “A net-linguistic ”Earley“ chart-parser.” To appear in: Reilly, R. Sc Sharkey, N. Connectionist approaches to language. Vol. 1. Amsterdam: North Holland.Google Scholar
- Wilkens, R. (1990) “Ein netzlinguistischer Parser für kontextfreie Phrasenstrukturgrammatiken” M.A. thesis. Ruhr-Universität Bochum, Sprachwissenschaftliches Institut.Google Scholar