Details
| Original language | English |
|---|---|
| Title of host publication | Findings of the Association for Computational Linguistics |
| Subtitle of host publication | ACL-IJCNLP 2021 |
| Editors | Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli |
| Pages | 1816-1827 |
| Number of pages | 12 |
| Publication status | Published - 2021 |
| Externally published | Yes |
| Event | Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 - Virtual, Online Duration: 1 Aug 2021 → 6 Aug 2021 |
Abstract
Text generation has received a lot of attention in computational argumentation research as of recently. A particularly challenging task is the generation of counter-arguments. So far, approaches primarily focus on rebutting a given conclusion, yet other ways to counter an argument exist. In this work, we go beyond previous research by exploring argument undermining, that is, countering an argument by attacking one of its premises. We hypothesize that identifying the argument's weak premises is key to effective countering. Accordingly, we propose a pipeline approach that first assesses the premises' strength and then generates a counter-argument undermining the weakest among them. On one hand, both manual and automatic evaluation underline the importance of identifying weak premises in counterargument generation. On the other hand, when considering correctness and content richness, human annotators favored our approach over state-of-the-art counter-argument baselines.
ASJC Scopus subject areas
- Arts and Humanities(all)
- Language and Linguistics
- Social Sciences(all)
- Linguistics and Language
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. ed. / Chengqing Zong; Fei Xia; Wenjie Li; Roberto Navigli. 2021. p. 1816-1827.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Counter-Argument Generation by Attacking Weak Premises
T2 - Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
AU - Alshomary, Milad
AU - Syed, Shahbaz
AU - Dhar, Arkajit
AU - Potthast, Martin
AU - Wachsmuth, Henning
N1 - Funding Information: This work was partially supported by the German Research Foundation (DFG) within the Collaborative Research Center “On-The-Fly Computing” (SFB 901/3) under the project number 160364472.
PY - 2021
Y1 - 2021
N2 - Text generation has received a lot of attention in computational argumentation research as of recently. A particularly challenging task is the generation of counter-arguments. So far, approaches primarily focus on rebutting a given conclusion, yet other ways to counter an argument exist. In this work, we go beyond previous research by exploring argument undermining, that is, countering an argument by attacking one of its premises. We hypothesize that identifying the argument's weak premises is key to effective countering. Accordingly, we propose a pipeline approach that first assesses the premises' strength and then generates a counter-argument undermining the weakest among them. On one hand, both manual and automatic evaluation underline the importance of identifying weak premises in counterargument generation. On the other hand, when considering correctness and content richness, human annotators favored our approach over state-of-the-art counter-argument baselines.
AB - Text generation has received a lot of attention in computational argumentation research as of recently. A particularly challenging task is the generation of counter-arguments. So far, approaches primarily focus on rebutting a given conclusion, yet other ways to counter an argument exist. In this work, we go beyond previous research by exploring argument undermining, that is, countering an argument by attacking one of its premises. We hypothesize that identifying the argument's weak premises is key to effective countering. Accordingly, we propose a pipeline approach that first assesses the premises' strength and then generates a counter-argument undermining the weakest among them. On one hand, both manual and automatic evaluation underline the importance of identifying weak premises in counterargument generation. On the other hand, when considering correctness and content richness, human annotators favored our approach over state-of-the-art counter-argument baselines.
UR - http://www.scopus.com/inward/record.url?scp=85123931225&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.findings-acl.159
DO - 10.18653/v1/2021.findings-acl.159
M3 - Conference contribution
AN - SCOPUS:85123931225
SN - 9781954085541
SP - 1816
EP - 1827
BT - Findings of the Association for Computational Linguistics
A2 - Zong, Chengqing
A2 - Xia, Fei
A2 - Li, Wenjie
A2 - Navigli, Roberto
Y2 - 1 August 2021 through 6 August 2021
ER -