Publication
Generierung natürlichsprachlicher Texte
Stephan Busemann
In: Günther Görz; Claus-Rainer Rollinger; Josef Schneeberger (Hrsg.). Handbuch der Künstlichen Intelligenz. Pages 783-814, Oldenbourg Wissenschaftsverlag, 2000.
Abstract
This short survey of the state of the art in natural language generation (NLG) in particular aims at readers interested in building practical systems. It defines language generation, identifies possible areas of application and describes the tasks a NLG system should fulfil. The interdependencies of the tasks are discussed and architecture models derived. The discussion of in-depth vs. shallow generation is based on the insight that different types of applications require different kinds of generators. A methodology for the design of NLG applications concludes the paper. (Note: The paper is written in German.