2026-07-072026-07-07http://salesiana.dossiersoluciones.com/handle/123456789/151041This paper describes an algorithm for the computation of FIRST and FOLLOW sets for use with feature-theoretic grammars in which the value of the sets consists of pairs of feature-theoretic categories. The algorithm preserves as much information from the grammars as possible, using negative restriction to define equivalence classes. Addition of a simple data structure leads to an order of magnitude improvement in execution time over a naive implementation.6 pages, COLING 94, compressed, uuencoded PostScript, 93KBComputation and Languagetext