A practical approach for representing context and for performing word sense disambiguation using neural networks

Summary form only given. The author proposes a method for representing context information so that the correct meaning for a word in a sentence can be selected. The approach is primarily based upon work by Waltz and Pollack, who emphasized neurally plausible systems. By contrast the author focuses upon computationally feasible methods applicable to full-scale natural language processing systems. There are two key elements: a collection of context vectors defined for every word used by a natural language processing system, and a context algorithm that computes a dynamic context vector at any position in a body of text. Once the dynamic context vector has been computed it is easy to choose among competing meanings for a word. This choice of definitions is essentially a neural network computation, and neural network learning algorithms should be able to improve the system´s choices. Good candidates for full-scale context vector implementations are machine translation systems and Japanese word processors