Claim Optimization in Computational Argumentation

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

Authors

External Research Organisations

  • University of Bremen
View graph of relations

Details

Original languageEnglish
Title of host publicationProceedings of the 16th International Natural Language Generation Conference
EditorsC. Maria Keet, Hung-Yi Lee, Sina Zarrieß
PublisherAssociation for Computational Linguistics (ACL)
Pages134-152
Number of pages19
ISBN (electronic)9798891760011
Publication statusPublished - Sept 2023
Event16th International Natural Language Generation Conference - Prag, Czech Republic
Duration: 11 Sept 202315 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

Cite this

Claim Optimization in Computational Argumentation. / Skitalinskaya, Gabriella; Spliethöver, Maximilian; Wachsmuth, Henning.
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 proceedingConference contributionResearchpeer review

Skitalinskaya, G, Spliethöver, M & Wachsmuth, H 2023, Claim Optimization in Computational Argumentation. in CM Keet, H-Y Lee & S Zarrieß (eds), Proceedings of the 16th International Natural Language Generation Conference. Association for Computational Linguistics (ACL), pp. 134-152, 16th International Natural Language Generation Conference, Prag, Czech Republic, 11 Sept 2023. https://doi.org/10.48550/arXiv.2212.08913, https://doi.org/10.18653/v1/2023.inlg-main.10
Skitalinskaya, G., Spliethöver, M., & Wachsmuth, H. (2023). Claim Optimization in Computational Argumentation. In C. M. Keet, H.-Y. Lee, & S. Zarrieß (Eds.), Proceedings of the 16th International Natural Language Generation Conference (pp. 134-152). Association for Computational Linguistics (ACL). https://doi.org/10.48550/arXiv.2212.08913, https://doi.org/10.18653/v1/2023.inlg-main.10
Skitalinskaya G, Spliethöver M, Wachsmuth H. Claim Optimization in Computational Argumentation. In Keet CM, Lee HY, Zarrieß S, editors, Proceedings of the 16th International Natural Language Generation Conference. Association for Computational Linguistics (ACL). 2023. p. 134-152 doi: 10.48550/arXiv.2212.08913, 10.18653/v1/2023.inlg-main.10
Skitalinskaya, Gabriella ; Spliethöver, Maximilian ; Wachsmuth, Henning. / Claim Optimization in Computational Argumentation. Proceedings of the 16th International Natural Language Generation Conference. editor / C. Maria Keet ; Hung-Yi Lee ; Sina Zarrieß. Association for Computational Linguistics (ACL), 2023. pp. 134-152
Download
@inproceedings{79d7f5f184a34a838fe6269abb17a4e4,
title = "Claim Optimization in Computational Argumentation",
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.",
author = "Gabriella Skitalinskaya and Maximilian Splieth{\"o}ver and Henning Wachsmuth",
note = "Publisher Copyright: {\textcopyright}2023 Association for Computational Linguistics.; 16th International Natural Language Generation Conference ; Conference date: 11-09-2023 Through 15-09-2023",
year = "2023",
month = sep,
doi = "10.48550/arXiv.2212.08913",
language = "English",
pages = "134--152",
editor = "Keet, {C. Maria} and Hung-Yi Lee and Sina Zarrie{\ss}",
booktitle = "Proceedings of the 16th International Natural Language Generation Conference",
publisher = "Association for Computational Linguistics (ACL)",
address = "Australia",

}

Download

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 -

By the same author(s)