Learning distributed representations of conceptual knowledge

Summary form only given, as follows. The authors argue that distributed representations must satisfy five criteria in order to serve as an adequate foundation for constructing and manipulating conceptual knowledge. These criteria are: automaticity, portability, structure encoding, semantic microcontent, and convergence. In the authors´ approach, distributed representations of semantic relations (i.e. propositions) are formed by recirculating the hidden layer in recurrent parallel distributed processing networks. The authors´ experiments show that the resulting distributed semantic representations (DSRs) satisfy all of the above criteria. They believe that DSRs can help supply an important building block in developing more complex connectionist architectures for higher level inferencing, as is required in natural language processing.<>