The major objective of the project is the development of methods for the automatic processing of natural medical language. Research focused on the theoretical and development issues of integrating medical text and the existing theorem prover for relevance/entailment predicate calculus with the Lexicographic Environment Software. The optimal way to store the continuum of text, from morpheme to discourse, was investigated. All components are designed to facilitate the adjoining of learning procedures to bear some of the task of developing detailed medical dictionaries and language processing procedures. Collaboration continued on the Clinical Information Utility with the Laboratory of Pathology, NCI/DCBD/LP, and with DCRT/DMB. Progress was made on obtaining and automatically encoding NIH surgical pathology data both from the Clinical Center Medical Information Science files, and from files covering the period 1959-1977.
