Preliminary Report On A Program For Generating Natural Langugage

Abstract

A pro&ram framework has been designed in which the linguistic facts and heuristics necessary for generating fluent natural langua&e can be encoded. The lin&uistic data is represented in annoteted procedures and data structures which are designed to make En&lish translations of already formulated messa&es given in a primary pro&ram's internal representation. The messa&es must include the program's intentions in saying them, in order to adequately specify the &rammatical operations required for a translation. The pertinant questions in this research have been: what structure does natural langua&e have that allows it to encode mutifaceted messages; and how must that structure be taken into account in the design of a &eneration facility for a computer prosram. This paper describes the control and data structures of the design and and their motivation. It is a condensation of my Master's Thesis <1>, to which the reader is refered for further information. Work is presently underwey on implementin& the desi&n in LISP end developing 1 &rammer for use in one or more of the domeins &iven below.