Automatic Linguistic Classification

6 1965 International Conference on Computational Linguistics AUTOmaTIC LINGUISTIC CLASSIFICATION E. D. Pendergraft and N. Dale Linguistics Research Center The University of Texas Austin i Texasl U. S. A. y ABSTRACT Many investisators have recognized that so- phisticated mechanical translation or other computational linguistic systems will require language learning capa- bilities, 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 ex- periments in automatic linguistic classification is de- scribed, together with a discussion of the first experi- ment 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. Pendergraft, Dale 1-1 INTRODUCTION Mechanical translation research over almost two decades has led to a broader discipline, computational linguistics, which already includes within its concern the automated processes that collect, store, retrieve or communicate information conveyed in or about language, as well as translate one language into another. Uith progress in automatic classification, another possibility is being explored, that of creating new information rather than merely gathering, maintaining or distributing the results of human intellectual activities. Many investigators have noted that sophisticated linguistic systems must be capable of learning. A new term may be defined within a text being translated me- chanically. Or, more commonly, a new meaning may be given a term used in close communication among colleagues. Bar-Hillel, for one, has waxed and waned in enthusiasm for mechanized linguistic learning, finally relegating even its investigators to the "lunatic fringe" of computational linguistics. Some thoughtful work has been done by Lamb [i] . Certainly Solomonoff [2] should be mentioned, as should Knowlton [3] and Sparck-Jones [4], but each for a different reason. There is hardly a literature to cite, unless it be that unruly assemblage we have come to call "artificial intelligence." The name "self-organizing system" has also come …

Content truncated to 500 words