Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)
Ronald Sumida, Michael Dyer
We present a Parallel Distributed Semantic (PDS) Network architecture that addresses the problems of sequencing and ambiguity resolution in natural language understanding. A PDS Network stores phrases and their meanings using multiple PDP networks, structured in the form of a se(cid:173) mantic net. A mechanism called Propagation Filters is employed: (1) to control communication between networks, (2) to properly sequence the components of a phrase, and (3) to resolve ambiguities. Simulation results indicate that PDS Networks and Propagation Filters can successfully rep(cid:173) resent high-level knowledge, can be trained relatively quickly, and provide for parallel inferencing at the knowledge level.