Details
| Original language | English |
|---|---|
| Title of host publication | EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference |
| Pages | 957-967 |
| Number of pages | 11 |
| ISBN (electronic) | 9781959429449 |
| Publication status | Published - 2023 |
| Event | 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Dubrovnik, Croatia Duration: 2 May 2023 → 6 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
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Software
- Social Sciences(all)
- Linguistics and Language
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
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 proceeding › Conference contribution › Research › peer review
}
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 -