Topic Ontologies for Arguments

Findings of the Association for Computational Linguistics: EACL 2023, pages 1411–1427 May 2-6, 2023 ©2023 Association for Computational Linguistics Topic Ontologies for Arguments Yamen Ajjour Lebiniz University Hannover Johannes Kiesel Bauhaus-Universität Weimar Benno Stein Bauhaus-Universität Weimar Martin Potthast Leipzig University and ScaDS.AI Abstract Many computational argumentation tasks, such as stance classification, are topic-dependent: The effectiveness of approaches to these tasks depends largely on whether they are trained with arguments on the same topics as those on which they are tested. The key question is: What are these training topics? To answer this question, we take the first step of mapping the argumentation landscape with The Argument Ontology (TAO). TAO draws on three authori- tative sources for argument topics: the World Economic Forum, Wikipedia’s list of controver- sial topics, and Debatepedia. By comparing the topics in our ontology with those in 59 argu- ment corpora, we perform the first comprehen- sive assessment of their topic coverage. While TAO already covers most of the corpus topics, the corpus topics barely cover all the topics in TAO. This points to a new goal for corpus construction to achieve a broad topic cover- age and thus better generalizability of compu- tational argumentation approaches. 1 Introduction The term “topic” refers to the subject matter of a text. A text may be about one or more topics and the relationship between topics and texts is called “aboutness” (Yablo, 2014). Topics play a central role in argumentation because they determine ar- gumentation strategies and rhetorical devices by setting the appropriate and expected universe of discourse. This view is supported by pragma- dialectics (van Eemeren, 2015): “The basic aspects of strategic maneuvering [. . . ] are making an expe- dient selection from the ‘topical potential’ available at a certain discussion.” Although debaters often use commonplace arguments across topics (Bilu et al., 2019), they must be relevant: a black market argument, for example, can be equally well applied to topics such as banning drugs or banning firearms. As recently shown, for example, by Reuver et al. (2021), training computational models to extract, analyze, or generate arguments with a broad topic coverage improves their generalizability. A set of topics can be organized as a graph, some- times called a “topic space”. Information theorists and library scientists map hierarchical subject re- lationships into ontologies in this way (Hjørland, 2001). For this purpose, topics are labeled with a subject heading, a phrase from a controlled vocabu- lary that describes a topic in a concise and discrim- inating manner. While library ontologies are not focused on argumentation, others deal specifically with argumentative topic spaces. We have identi- fied and tapped three authoritative sources of onto- logical knowledge covering global issues, contro- versies, and popular debates: the World Economic Forum’s “Strategic Intelligence” site, Wikipedia’s list of controversial topics, and Debatepedia’s de- bate classification system (Section 4). They form the basis for The Argument Ontology (TAO).1 We compile a comprehensive survey of 59 argu- ment corpora ( Section 3) and investigate their topic coverage …

Content truncated to 500 words