This article challenges the received wisdom that template-based approaches to the generation of language are necessarily inferior to other approaches as regards their maintainability, linguistic well-foundedness, and quality of output. Some recent NLG systems that call themselves “template-based” will illustrate our claims.

This content is only available as a PDF.

Author notes

Computing Science Department, King's College, University of Aberdeen, United Kingdom. [email protected]

Communication and Cognition/Computational Linguistics, Faculty of Arts, Tilburg University, Tilburg, The Netherlands. [email protected]

Human Media Interaction Group, Computer Science, University of Twente, The Netherlands. [email protected]