A Biologically Inspired Connectionist System for Natural Language Processing

Nowadays artificial neural network models often lack many physiological properties of the nervous cell. Feedforward multilayer perceptron architectures, and even simple recurrent networks, still in vogue, are far from those encountered in cerebral cortex. Current learning algorithms are more oriented to computational performance than to biological credibility. The aim of this paper is to propose an artificial neural network system, called Bio-θR, including architecture and algorithm, to take care of a natural language processing problem, the thematic relationship, in a biologically inspired connectionist approach. Instead of feedforward or simple recurrent network, it is presented a bi-directional architecture. Instead of the well-known biologically implausible backpropagation algorithm, a neurophysiologically motivated one is employed to account for linguistic thematic role assignment in natural language sentences. In addition, several features concerning biological plausibility are also included.