Topic Ontologies for Arguments

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Bauhaus-Universität Weimar
  • Leipzig University
View graph of relations

Details

Original languageEnglish
Title of host publicationEACL 2023
Subtitle of host publication17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023
Pages1381-1397
Number of pages17
ISBN (electronic)9781959429470
Publication statusPublished - 2023
Event17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 - Dubrovnik, Croatia
Duration: 2 May 20236 May 2023

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 authoritative sources for argument topics: the World Economic Forum, Wikipedia’s list of controversial topics, and Debatepedia. By comparing the topics in our ontology with those in 59 argument corpora, we perform the first comprehensive 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 coverage and thus better generalizability of computational argumentation approaches.

ASJC Scopus subject areas

Cite this

Topic Ontologies for Arguments. / Ajjour, Yamen; Stein, Benno; Kiesel, Johannes et al.
EACL 2023 : 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023. 2023. p. 1381-1397.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Ajjour, Y, Stein, B, Kiesel, J & Potthast, M 2023, Topic Ontologies for Arguments. in EACL 2023 : 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023. pp. 1381-1397, 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023, Dubrovnik, Croatia, 2 May 2023.
Ajjour, Y., Stein, B., Kiesel, J., & Potthast, M. (2023). Topic Ontologies for Arguments. In EACL 2023 : 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023 (pp. 1381-1397)
Ajjour Y, Stein B, Kiesel J, Potthast M. Topic Ontologies for Arguments. In EACL 2023 : 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023. 2023. p. 1381-1397
Ajjour, Yamen ; Stein, Benno ; Kiesel, Johannes et al. / Topic Ontologies for Arguments. EACL 2023 : 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023. 2023. pp. 1381-1397
Download
@inproceedings{00d99d239000476b96d582b300ac50fe,
title = "Topic Ontologies for Arguments",
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 authoritative sources for argument topics: the World Economic Forum, Wikipedia{\textquoteright}s list of controversial topics, and Debatepedia. By comparing the topics in our ontology with those in 59 argument corpora, we perform the first comprehensive 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 coverage and thus better generalizability of computational argumentation approaches.",
author = "Yamen Ajjour and Benno Stein and Johannes Kiesel and Martin Potthast",
year = "2023",
language = "English",
pages = "1381--1397",
booktitle = "EACL 2023",
note = "17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 ; Conference date: 02-05-2023 Through 06-05-2023",

}

Download

TY - GEN

T1 - Topic Ontologies for Arguments

AU - Ajjour, Yamen

AU - Stein, Benno

AU - Kiesel, Johannes

AU - Potthast, Martin

PY - 2023

Y1 - 2023

N2 - 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 authoritative sources for argument topics: the World Economic Forum, Wikipedia’s list of controversial topics, and Debatepedia. By comparing the topics in our ontology with those in 59 argument corpora, we perform the first comprehensive 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 coverage and thus better generalizability of computational argumentation approaches.

AB - 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 authoritative sources for argument topics: the World Economic Forum, Wikipedia’s list of controversial topics, and Debatepedia. By comparing the topics in our ontology with those in 59 argument corpora, we perform the first comprehensive 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 coverage and thus better generalizability of computational argumentation approaches.

UR - http://www.scopus.com/inward/record.url?scp=85159853290&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85159853290

SP - 1381

EP - 1397

BT - EACL 2023

T2 - 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023

Y2 - 2 May 2023 through 6 May 2023

ER -

By the same author(s)