DocumentCode
3287137
Title
A connectionist model of conceptual representation
Author
Weber
Author_Institution
Dept. of Comput. Sci., Rochester Univ., NY, USA
fYear
1989
fDate
0-0 1989
Firstpage
477
Abstract
A description is given of a connectionist architecture for modeling conceptual representation. Connectionist structures for capturing property-value bindings, conceptual aspects, scalar properties, property abstraction and inheritance, and category error detection are described. With these structures, the system known as DIFICIL (Direct Inferences and Figurative Interpretation in a Connectonist Implementation of Language comprehension) is able to perform direct inferences, both immediate and mediated, and interpret both literal and figurative adjective-noun combinations.<>
Keywords
inference mechanisms; neural nets; DIFICIL; category error detection; conceptual representation; connectionist model; direct inferences; inference mechanisms; inheritance; neural nets; property abstraction; property-value bindings; scalar properties; Inference mechanisms; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location
Washington, DC, USA
Type
conf
DOI
10.1109/IJCNN.1989.118622
Filename
118622
Link To Document