System Name
B2Z list of NLG systems
System Builders Carenini
Development Dates 2000-2002
Languages English
URL (if available)
who's who


GEA is a fully-implemented, complete and modular NLG system for generating user tailored evaluative arguments. GEA covers all aspects of generating evaluative arguments from selecting and organizing the content of the argument, to expressing the selected content into natural language. For content selection and organization, GEA applies an argumentation strategy based on guidelines from argumentation theory. For expressing the content into natural language, GEA relies on a set of techniques that extend and integrate previous work in computational linguistics on micro-planning and realizing evaluative arguments. Finally, a quantitative model of user preferences expressed as an additive multiattribute value function (AMVF) is the key knowledge source used by GEA in tailoring the content, organization and phrasing of the generated arguments to its users.


Main reference

Giuseppe Carenini.
GEA: a Complete, Modular System for Generating Evaluative Arguments.
In International workshop on Computational Models of Natural Language Argument, San Francisco, California, 2001.

Giuseppe Carenini and Johanna Moore.
A strategy for generating Evaluative Arguments.
In Proceedings of the International Natural Language Generation Conference (INLG-2000), Mitzpe Ramon, Israel, 2000.

Information last updated: 21.05.2005 (
Page last generated: 25-1-2009 21:01:38