Integrating connectionist and symbolic computation for the theory of language
Paul Smolensky, Géraldine Légendre, Yosbiro Miyata · 1993
... or so, neural or connectionist networks have produced an explosion of results and a great deal of interest. Yet this approach to the computational modeling of intelligent cognitive systems faces fundamental problems. The research proposed here has a major connectionist component, but it distinguishes itself from the bulk of connectionist research in the following respects: (0) a. It is strongly guided by symbolic computation, but not a "hybrid" in the usual sense: the connectionist and symbolic computation involved are not two components of a composite system, but two descriptions of a single system. We call this "integrated connection- ist/symbolic computation." b. The emphasis is on higher level cognitive processes, with a main focus on language, which provides a particularly chaJJenging testbed, since symbolic computation is so central to existing theory. c. The main emphasis in the language research is on formal grammars for natural language, with supporting research on the gram