During the last decade, connectionism has increasingly received attention within a variety of research disciplines. In this contribution, we focus on the role of connectionist modeling within the domain of natural language processing (NLP) and, more specifically, on pragmatics. As a computational theory, connectionism has led to significant developments in modeling cognitive processes. Rumelhart & McClelland, in their influential two-volume handbook, characterize connectionist modeling as providing

References

Elman, J.

1990 Finding structure in time. Cognitive Science 14: 179–211.

Fodor, J. & Z. W. Pylyshyn

1988 Connectionism and cognitive architecture. Cognition 28: 2–71.

Hinton, G.

1990 Connectionist symbol processing. Special issue of Artificial Intelligence .

Kohonen, T.

1984 Self-organisation and associative memory. Springer.

Lee, G. & M. Flowers & M. Dyer

1990 Learning distributed representations and their application to script-based story processing. Connection Science 2: 313–345.

Mannes, S. & S. Doane

1991 A hybrid model of script generation. Connection Science 3: 61–87.

Miikkulainen, R.

1993 Subsymbolic natural language processing. MIT Press.

Minsky, M. L. & S. A. Papert

1988 Perceptrons. MIT Press.

Reilley, R. G. & N. E. Sharkey

(eds.) 1992 Connectionist approaches to natural language processing. Lawrence Erlbaum.

Rosenblatt, F.

1958 The perceptron. Psychological Review 65: 368–408.

Rumelhart, D. E. & G. E. Hinton & R. J. Williams

1986 Learning internal representations by error propagation. In D. E. Rumelhart & J. L. Mcclelland (eds.): 318–362.

Rumelhart, D. E. & J. L. Mcclelland

(eds.) 1986 Parallel distributed processing (vol. 1). MIT Press.

Schank, R. C. & R. Abelson

1977 Script, plans, goals and understanding. Erlbaum.

Sejnowski, T. J. & C. S. Rosenberg

1987 Parallel networks that learn to pronounce English text. Complex Systems 1: 145–168.

Servan-Schreiber, D. & A. Cleeremans & J. L. Mcclelland

1991 Graded state machines. Machine Learning 7: 161–193.