Title :
A connectionist inference mechanism for a natural language understanding system
Author :
Lalitrojwong, Pattarachai ; Buchheit, Paul ; Evens, Martha W.
Author_Institution :
Fac. of Inf. Technol., King Mongkut´´s Inst. of Technol., Bangkok, Thailand
Abstract :
We have developed the Connectionist Inference Mechanism (CIM) to serve as a connectionist alternative to the symbolic inference module of P. Buchheit´s (1991) Informational Network For A Natural Thinking (INFANT) System. CIM consists of several modules working together, including memory, neural networks, and a binding set. Its main task is to perform inference generation with the capability of variable binding. CIM is essentially a hybrid cognitive model that combines the advantages of a symbolic approach, local representation, and parallel distributed processing. It can be shown that each approach complements and supports the others
Keywords :
cognitive systems; inference mechanisms; natural languages; neural nets; CIM; INFANT System; Informational Network For A Natural Thinking System; binding set; connectionist alternative; connectionist inference mechanism; hybrid cognitive model; inference generation; local representation; natural language understanding system; neural networks; parallel distributed processing; symbolic approach; symbolic inference module; variable binding; Computer integrated manufacturing; Computer science; Distributed processing; Educational institutions; Inference mechanisms; Information technology; Lakes; Natural language processing; Natural languages; Neural networks;
Conference_Titel :
Information Intelligence and Systems, 1999. Proceedings. 1999 International Conference on
Conference_Location :
Bethesda, MD
Print_ISBN :
0-7695-0446-9
DOI :
10.1109/ICIIS.1999.810349
