Conclusion-based Counter-Argument Generation

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

Authors

Research Organisations

View graph of relations

Details

Original languageEnglish
Title of host publicationEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Pages957-967
Number of pages11
ISBN (electronic)9781959429449
Publication statusPublished - 2023
Event17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Dubrovnik, Croatia
Duration: 2 May 20236 May 2023

Abstract

In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. Existing work on the automatic generation of natural language counter-arguments does not address the relation to the conclusion, possibly because many arguments leave their conclusion implicit. In this paper, we hypothesize that the key to effective counter-argument generation is to explicitly model the argument's conclusion and to enforce that the stance of the generated counter is opposite to that conclusion. In particular, we propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument. The approach employs a stance-based ranking component that selects the counter from a diverse set of generated candidates whose stance best opposes the generated conclusion. In both automatic and manual evaluation, we provide evidence that our approach generates more relevant and stance-adhering counters than strong baselines.

ASJC Scopus subject areas

Cite this

Conclusion-based Counter-Argument Generation. / Alshomary, Milad; Wachsmuth, Henning.
EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. 2023. p. 957-967.

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

Alshomary, M & Wachsmuth, H 2023, Conclusion-based Counter-Argument Generation. in EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. pp. 957-967, 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023, Dubrovnik, Croatia, 2 May 2023. https://doi.org/10.48550/arXiv.2301.09911
Alshomary, M., & Wachsmuth, H. (2023). Conclusion-based Counter-Argument Generation. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 957-967) https://doi.org/10.48550/arXiv.2301.09911
Alshomary M, Wachsmuth H. Conclusion-based Counter-Argument Generation. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. 2023. p. 957-967 Epub 2023 Jan 24. doi: 10.48550/arXiv.2301.09911
Alshomary, Milad ; Wachsmuth, Henning. / Conclusion-based Counter-Argument Generation. EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. 2023. pp. 957-967
Download
@inproceedings{3c8a715987684dc2b406d090ebaad22a,
title = "Conclusion-based Counter-Argument Generation",
abstract = "In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. Existing work on the automatic generation of natural language counter-arguments does not address the relation to the conclusion, possibly because many arguments leave their conclusion implicit. In this paper, we hypothesize that the key to effective counter-argument generation is to explicitly model the argument's conclusion and to enforce that the stance of the generated counter is opposite to that conclusion. In particular, we propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument. The approach employs a stance-based ranking component that selects the counter from a diverse set of generated candidates whose stance best opposes the generated conclusion. In both automatic and manual evaluation, we provide evidence that our approach generates more relevant and stance-adhering counters than strong baselines.",
author = "Milad Alshomary and Henning Wachsmuth",
note = "Funding Information: This work was funded by the Deutsche Forschungs-gemeinschaft (DFG, German Research Foundation): TRR 318/1 2021 - 438445824. We would also like to thank the reviewers and the participants who took part anonymously in our user study.; 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 ; Conference date: 02-05-2023 Through 06-05-2023",
year = "2023",
doi = "10.48550/arXiv.2301.09911",
language = "English",
pages = "957--967",
booktitle = "EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",

}

Download

TY - GEN

T1 - Conclusion-based Counter-Argument Generation

AU - Alshomary, Milad

AU - Wachsmuth, Henning

N1 - Funding Information: This work was funded by the Deutsche Forschungs-gemeinschaft (DFG, German Research Foundation): TRR 318/1 2021 - 438445824. We would also like to thank the reviewers and the participants who took part anonymously in our user study.

PY - 2023

Y1 - 2023

N2 - In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. Existing work on the automatic generation of natural language counter-arguments does not address the relation to the conclusion, possibly because many arguments leave their conclusion implicit. In this paper, we hypothesize that the key to effective counter-argument generation is to explicitly model the argument's conclusion and to enforce that the stance of the generated counter is opposite to that conclusion. In particular, we propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument. The approach employs a stance-based ranking component that selects the counter from a diverse set of generated candidates whose stance best opposes the generated conclusion. In both automatic and manual evaluation, we provide evidence that our approach generates more relevant and stance-adhering counters than strong baselines.

AB - In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. Existing work on the automatic generation of natural language counter-arguments does not address the relation to the conclusion, possibly because many arguments leave their conclusion implicit. In this paper, we hypothesize that the key to effective counter-argument generation is to explicitly model the argument's conclusion and to enforce that the stance of the generated counter is opposite to that conclusion. In particular, we propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument. The approach employs a stance-based ranking component that selects the counter from a diverse set of generated candidates whose stance best opposes the generated conclusion. In both automatic and manual evaluation, we provide evidence that our approach generates more relevant and stance-adhering counters than strong baselines.

UR - http://www.scopus.com/inward/record.url?scp=85159856327&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2301.09911

DO - 10.48550/arXiv.2301.09911

M3 - Conference contribution

AN - SCOPUS:85159856327

SP - 957

EP - 967

BT - EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

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

Y2 - 2 May 2023 through 6 May 2023

ER -

By the same author(s)