Natural Language Generation

What is it? Natural language generation is concerned with constructing computational systems that automatically generate texts of all kinds based on some non-linguistic input (such as a database) and some communicative goals. This requires both linguistic knowledge—ranging from morphology to text structure—and computational knowledge, for making the entire thing actually work. Natural language generation, or NLG, is therefore of both theoretical and practical interest.

I have written several introductions to NLG and the state of the art: an open-ended starting point can be found here. The bibliographical references to further work and reading are extensive. My bibliography page also contains considerable further materials.


An almost complete list of natural language generation systems can be found here organized as a Wiki..

I have been developing and supporting the multilingual generation system and grammar development environment KPML since 1994. For more information on usage, coverage and availability, see the KPML website.

John Bateman, February 2018