AUTOMATIC GENERATION OF TECHNICAL DOCUMENTATION

Abstract

Natural-language generation (NLG) techniques can be used to automatically produce technical documentation from a domain knowledge base and linguistic and contextual models. We discuss this application of NLG technology from both a technical and a usefulness (costs and benefits) perspective. This discussion is based largely on our experiences with the Intelligent Documentation Advisory System (IDAS) documentation-generation project, and the reactions that various interested people from industry have had to IDAS. We hope that this summary of our experiences with IDAS and the lessons we have learned from it will be beneficial for other researchers who wish to build technical documentation-generation systems.

Additional information

Notes on contributors

EHUD REITER

Address correspondence to Dr. Ehud Reiter, Department of Computing Science, University of Aberdeen, King's College, Aberdeen AB9 2UE United Kingdom; E-mail;[email protected]; or to Dr. Chris Mellish, Department of Artificial Intelligence, University of Edinburgh, 80 South Bridge, Edinburgh EHI IHN, United Kingdom; E-mail;[email protected].