AgTnnCtAL ~G~CE 163 Extending the Expressive Power of Semantic Networks

"'Factual knowledge " Used by natural ang._~_o~e processing systems can be cor~niently represented in the form of semantic networks. Compared to a "linear " representation such as that of I ~ Pre~dicate Calculus however, semantic networks present special problems with respect to the use of logical connectives, quantiflers, descriptions, and certain other construc-timts? sy~fe/~tt ¢ solutions to these problems will be proposed, in the form Of extensions toa more or less conventionalnetwork notation. Predicate Calculus tranzlottons of network 'propositions will freq~,ntly be given for comparison, toillustrate the close kltt~p of the two forms of representation.,. I. Iatrd~ellm Semantic networks (cr nets) mean different things to different ~ople. They are variously thought of as diagrams on paper, as abstractsets of n-tuples of some sort, as data structures in computers, or even as information structures in brains. My concern here will be with semantic nets as graphical analogues of data structures representing "facts " in a computer system for understanding natural anguage. My point of view is that o rs heuristic programmer. For discussions of the place of semantic nets in psycholog~ca! the0fies of cognition see, for example, Anderson an6 Bower [2] and Wikon.[42, 43]. Semantic nets aid both in the formulation and exposition of the computer data structures they resemble. Example ~ of such graphical aids are found in the work of Quillian [23, 24], palme [22], schank [32, 33], Simmons an