Natural Language Sourcebook
Walter Read, Michael G. Dyer, Eva L. Baker, Patricia Mutch, Frances A. Butler · 1990
Abstract : The Natural Language Sourcebook was a research component in the development of the Artificial Intelligence Measurement System (AIMS). The Sourcebook is a compilation on 197 processing problems addressed or handled by intelligent computer systems. The problems, culled from the literature in artificial intelligence, computational linguistics, and cognitive psychology, have been classified into a scheme with an artificial intelligence bent and cross-referenced to companion schemes one with a linguistic and one with a cognitive psychological perspective on the type of issues reflected in the problems. Each entry in the Sourcebook, called and exemplar, consists of (1) one or more sentences, a fragment of dialogue or a piece of text which illustrates a conceptual issue, (2) a reference, and (3) a discussion of the problem a system might have in understanding the example. An electronic version of the Sourcebook database was developed in a Hypercard environment to facilitate use of the multiple classification schemes (Herl, September 1990). The Hypercard version of the Sourcebook is accompanied by a user's manual (Herl, August 1990).