ABSTRACT
We constructed a Modular Connectionist Architecture which consists of many different types of 3 layer feed-forward PDP network modules (auto-associative recurrent, hetero-associative recurrent, and hetero-associative) in order to do script-based story understanding. Our system, called DYNASTY (DYNAmic script-based STory understanding sYstem) has the following 3 major functions: (1) DYNASTY can learn distributed representations of concepts and events in everyday scriptal experiences, (2) DYNASTY can do script-based causal chain completion inferences according to the acquired sequential knowledge, and (3) DYNASTY performs script role association and retrieval while performing script application. Our purpose in constructing this system is to show that the learned internal representations, using simple encoder-type networks, can be used in higher-level modules to develop connectionist architectures for fairly complex cognitive tasks, such as script processing. Unlike other neurally inspired script processing models, DYNASTY can learn its own similarity-based distributed representations from input script data using ARPDP (Auto-associative Recurrent PDP) architectures. Moreover DYNASTY's role association network handles both script roles and fillers as full-fledged concepts, so that it can learn the generalized associative knowledge between several script roles and fillers.
