Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 16th International Natural Language Generation Conference |
| Editors | C. Maria Keet, Hung-Yi Lee, Sina Zarrieß |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 134-152 |
| Number of pages | 19 |
| ISBN (electronic) | 9798891760011 |
| Publication status | Published - Sept 2023 |
| Event | 16th International Natural Language Generation Conference - Prag, Czech Republic Duration: 11 Sept 2023 → 15 Sept 2023 |
Abstract
An optimal delivery of arguments is key to persuasion in any debate, both for humans and for AI systems. This requires the use of clear and fluent claims relevant to the given debate. Prior work has studied the automatic assessment of argument quality extensively. Yet, no approach actually improves the quality so far. To fill this gap, this paper proposes the task of claim optimization: to rewrite argumentative claims in order to optimize their delivery. As multiple types of optimization are possible, we approach this task by first generating a diverse set of candidate claims using a large language model, such as BART, taking into account contextual information. Then, the best candidate is selected using various quality metrics. In automatic and human evaluation on an English-language corpus, our quality-based candidate selection outperforms several baselines, improving 60% of all claims (worsening 16% only). Follow-up analyses reveal that, beyond copy editing, our approach often specifies claims with details, whereas it adds less evidence than humans do. Moreover, its capabilities generalize well to other domains, such as instructional texts.
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Information Systems
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 16th International Natural Language Generation Conference. ed. / C. Maria Keet; Hung-Yi Lee; Sina Zarrieß. Association for Computational Linguistics (ACL), 2023. p. 134-152.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Claim Optimization in Computational Argumentation
AU - Skitalinskaya, Gabriella
AU - Spliethöver, Maximilian
AU - Wachsmuth, Henning
N1 - Publisher Copyright: ©2023 Association for Computational Linguistics.
PY - 2023/9
Y1 - 2023/9
N2 - An optimal delivery of arguments is key to persuasion in any debate, both for humans and for AI systems. This requires the use of clear and fluent claims relevant to the given debate. Prior work has studied the automatic assessment of argument quality extensively. Yet, no approach actually improves the quality so far. To fill this gap, this paper proposes the task of claim optimization: to rewrite argumentative claims in order to optimize their delivery. As multiple types of optimization are possible, we approach this task by first generating a diverse set of candidate claims using a large language model, such as BART, taking into account contextual information. Then, the best candidate is selected using various quality metrics. In automatic and human evaluation on an English-language corpus, our quality-based candidate selection outperforms several baselines, improving 60% of all claims (worsening 16% only). Follow-up analyses reveal that, beyond copy editing, our approach often specifies claims with details, whereas it adds less evidence than humans do. Moreover, its capabilities generalize well to other domains, such as instructional texts.
AB - An optimal delivery of arguments is key to persuasion in any debate, both for humans and for AI systems. This requires the use of clear and fluent claims relevant to the given debate. Prior work has studied the automatic assessment of argument quality extensively. Yet, no approach actually improves the quality so far. To fill this gap, this paper proposes the task of claim optimization: to rewrite argumentative claims in order to optimize their delivery. As multiple types of optimization are possible, we approach this task by first generating a diverse set of candidate claims using a large language model, such as BART, taking into account contextual information. Then, the best candidate is selected using various quality metrics. In automatic and human evaluation on an English-language corpus, our quality-based candidate selection outperforms several baselines, improving 60% of all claims (worsening 16% only). Follow-up analyses reveal that, beyond copy editing, our approach often specifies claims with details, whereas it adds less evidence than humans do. Moreover, its capabilities generalize well to other domains, such as instructional texts.
UR - http://www.scopus.com/inward/record.url?scp=105016536909&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2212.08913
DO - 10.48550/arXiv.2212.08913
M3 - Conference contribution
SP - 134
EP - 152
BT - Proceedings of the 16th International Natural Language Generation Conference
A2 - Keet, C. Maria
A2 - Lee, Hung-Yi
A2 - Zarrieß, Sina
PB - Association for Computational Linguistics (ACL)
T2 - 16th International Natural Language Generation Conference
Y2 - 11 September 2023 through 15 September 2023
ER -