Title :
A connectionist model of conceptual representation
Author_Institution :
Dept. of Comput. Sci., Rochester Univ., NY, USA
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;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118622
