On natural language generation of formal argumentation
MetadataShow full item record
Altmetrics Handle Statistics
In this paper we provide a first analysis of the research questions that arise when dealing with the problem of communicating pieces of formal argumentation through natural language interfaces. It is a generally held opinion that formal models of argumentation naturally capture human argument, and some preliminary studies have focused on justifying this view. Unfortunately, the results are not only inconclusive, but seem to suggest that explaining formal argumentation to humans is a rather articulated task. Graphical models for expressing argumentation-based reasoning are appealing, but often humans require significant training to use these tools effectively. We claim that natural language interfaces to formal argumentation systems offer a real alternative, and may be the way forward for systems that capture human argument.
Cerutti , F , Toniolo , A & Norman , T J 2019 , On natural language generation of formal argumentation . in F Santini & A Toniolo (eds) , Proceedings of the 3rd Workshop on Advances In Argumentation In Artificial Intelligence co-located with the 18th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2019) : Rende, Italy, November 19-22, 2019 . CEUR Workshop Proceedings , vol. 2528 , Sun SITE Central Europe , pp. 15-29 , 3rd Workshop on Advances In Argumentation In Artificial Intelligence, AI^3 2019 , Rende , Italy , 19/11/19 . < http://ceur-ws.org/Vol-2528/ >conference
Proceedings of the 3rd Workshop on Advances In Argumentation In Artificial Intelligence co-located with the 18th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2019)
Copyright © 2019 the Author(s). Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.