Spreading Activation and Connectionist Models for Natural Language Processing

TitleSpreading Activation and Connectionist Models for Natural Language Processing
Publication TypeTechnical Report
Year of Publication1989
AuthorsDiederich, J.
Other Numbers507
Abstract

High level cognitive tasks performed by an artificial neural network require both knowledge over a domain and inferencing abilities. To operate in a complex, natural environment neural networks must have robust, reliable and massively parallel inference mechanisms. This paper describes various spreading activation and connectionist mechanisms for inferencing as part of natural language processing systems, including possible techniques to enrich these systems by machine learning. In particular models which attack one or more important problems such as variable binding, knowledge-intensive learning, avoidance of cross-talk and false classifications are selected for this overview.

URLhttp://www.icsi.berkeley.edu/pubs/techreports/tr-89-008.pdf
Bibliographic Notes

ICSI Technical Report TR-89-008

Abbreviated Authors

J. Diederich

ICSI Publication Type

Technical Report