... adequate for learning the complexities of real natural language (e.g. (Fodor and Pylyshyn, 1988), (Hender- son, 1996)). Work on extending connectionist architectures for application to complex ... pattern for the gestalt inputs is straightforward, since these inputs per- tain to information about the sentence as a whole. Whenever a tag is input to the network, the activa- tion pattern for ... constituency to be represented, but to date there has been no empirical demonstration of how a learning algorithm can be effectively applied to such a network. In this paper we propose an architecture...