Publication Details

Title: Spreading Activation and Connectionist Models for Natural Language Processing
Author: J. Diederich
Group: ICSI Technical Reports
Date: February 1989
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-89-008.pdf

Overview:
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.

Bibliographic Information:
ICSI Technical Report TR-89-008

Bibliographic Reference:
J. Diederich. Spreading Activation and Connectionist Models for Natural Language Processing. ICSI Technical Report TR-89-008, February 1989