Sentence Comprehension: A Parallel Distributed Processing Approach
CARNEGIE-MELLON UNIV PITTSBURGH PA ARTIFICIAL INTELLIGENCE AND PSYCHOLOGY PROJECT
Pagination or Media Count:
Basic aspects are reviewed of conventional approaches to sentence comprehension and point out are some of the difficulties faced by models that take these approaches. An alternative approach is described, based on the principles of parallel distributed processing, and shown how it offers different answers to basic questions about the nature of the language processing mechanism. An illustrative simulation model captures the key characteristics of the approach, and illustrates how it can cope with the difficulties faced by conventional models. Alternative ways of conceptualizing basic aspects of language processing within the framework of this approach will consider how it can address several arguments that might be brought to bear against it, and suggest avenues for future development. Keywords Neural networks Connectionist models Language comprehension Language acquisition.