This report comprises two documents which describe the state of the art of computer generation of natural language text. Both were prepared by a panel of individuals who are active in research on text generation. The first document assesses the techniques now available for use in systems design, covering all of the technical methods by which computer programs create and present English text in their outputs, and identifies four kinds of technical developments which will shape the art in the coming decade: linguistically justified grammars, knowledge representation methods, models of the reader, and models of discourse. A comprehensive bibliography on text generation, the second document lists published works on the generation of natural language text by computer programs and some prior noncomputational work that has been used as a basis for such computer programs. Seven brief descriptions are included for research in progress or research recently completed but not yet described comprehensively in any publication. (Author/LMM)