Connectionist Natural Language Processing: A Status Report

The summation and thresholding of activation allows for smooth integration of multiple sources of knowledge and the hope is that connectionist approaches to NLP will replace the more traditional, symbolic approaches toNLP.

Abstract

Connectionist networks (CNs) exhibit many useful properties. Their spreading activation processes are inherently parallel in nature and support associative retrieval of memories. The summation and thresholding of activation allows for smooth integration of multiple sources of knowledge. CNs with distributed representations () exhibit robustness in the face of noise/damage and can learn to perform complex mapping tasks just from examples. Connectionist networks are also able to dynamically reinterpret situations as new inputs are received. These features are very useful for natural language processing (NLP) and offer the hope that connectionist approaches to NLP will replace the more traditional, symbolic approaches to NLP.