Automatic linguistic classification
E. D. Pendergraft, Nell B. Dale · 1965
Many investigators have recognized that sophisticated mechanical translation or other computational linguistic systems will require language learnign capabilities, both in the ability to discover and verify new descriptive rules, and to adapt rules to new situations of use.The work plan of a long-range series of experiments in automatic linguistic classification is described, together with a discussion of the first experiment now in progress. The latter is concerned with category identification. In particular the data resulting from automatic syntactic analysis of English texts will be used to identify syntactic categories which have similar membership.The series of experiments will accordingly combine the use of automatic linguistic analysis and automatic classification techniques. Automatic syntactic analysis, and in later experiments semantic analysis, will be performed within the Linguistics Research System (LRS). Automatic classification will be carried out within the Automatic Classification System (ACS). Both of these computer systems have been developed by the Linguistics Research Center.LRS is a large-capacity system designed especially to support research in computational linguistics. It currently has the capability of performing several types of generalized translation, and of transferring information among any number of languages through the use of interlingual descriptions. This system operates under its own monitor.ACS is a Fortran IV system operating under the IBSYS monitor. It performs a variety of classification operations on large universes of objects having specified properties. Either objects or properties may be classified, and correlations may be computed among resulting classes.A programming interface is being constructed between these two systems so that their combined capabilities can be used for automatic linguistic classification.