Biological and Cognitive Plausibility in Connectionist Networks for Language Modeling

If we want to explain cognitive processes with means of connectionist networks, these networks have to correspond with cognitive systems and their underlying biological mechanisms in different respects. The question of biological and cognitive plausibility of connectionist models arises from two different aspects – first, from the aspect of biology – on one hand, one has to have a fair understanding of biological mechanisms and cognitive mechanisms in order to represent them in a model, and on the other hand there is the aspect of modeling – one has to know how to construct a model to represent precisely what we are aiming at. Computer power and modeling techniques have improved dramatically in recent 20 years, so the plausibility problem is being addressed in more adequate ways as well. Connectionist models are often used for representing different aspects of natural language. Their biological plausibility had sometimes been questioned in the past. Today, the field of computational neuroscience offers several acceptable possibilities of modeling higher cognitive functions, and language is among them. This paper brings a presentation of some existing connectionist networks modeling natural language. The question of their explanatory power and plausibility in terms of biological and cognitive systems they are representing is discussed