We will discuss various connectionist schemes for natural language understanding (NLU). In principle, massively parallel processing schemes, such as connectionist networks, are well-suited for modelling highly integrated forms of processing. The connectionist approach towards natural language processing is motivated by the belief that a NLU system should process knowledge from many different sources, e.g. semantic, syntactic, and pragmatic, in just this sort of integrated manner. The successful use of spreading activation for various disambiguation tasks in natural language processing models lead to the first connectionist NLU systems. In addition to describing in detail a connectionist disambiguation system, we will also discuss proposed connectionist approaches towards parsing and case role assignment. This paper is intended to introduce the reader to some of the basic ideas behind the connectionist approach to NLU. We will also suggest some directions for future research.