To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

Externe Organisationen

  • Universität Bremen
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Seiten15799–15816
Seitenumfang17
ISBN (elektronisch)9781959429722
PublikationsstatusVeröffentlicht - Juli 2023
Veranstaltung61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Kanada
Dauer: 9 Juli 202314 Juli 2023

Publikationsreihe

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Band1
ISSN (Print)0736-587X

Abstract

Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In this work, we explore the main challenges to identifying argumentative claims in need of specific revisions. By learning from collaborative editing behaviors in online debates, we seek to capture implicit revision patterns in order to develop approaches aimed at guiding writers in how to further improve their arguments. We systematically compare the ability of common word embedding models to capture the differences between different versions of the same text, and we analyze their impact on various types of writing issues. To deal with the noisy nature of revision-based corpora, we propose a new sampling strategy based on revision distance. Opposed to approaches from prior work, such sampling can be done without employing additional annotations and judgments. Moreover, we provide evidence that using contextual information and domain knowledge can further improve prediction results. How useful a certain type of context is, depends on the issue the claim is suffering from, though.

ASJC Scopus Sachgebiete

Zitieren

To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support. / Skitalinskaya, Gabriella; Wachsmuth, Henning.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023. S. 15799–15816 (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Band 1).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Skitalinskaya, G & Wachsmuth, H 2023, To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support. in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Proceedings of the Annual Meeting of the Association for Computational Linguistics, Bd. 1, S. 15799–15816, 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023, Toronto, Kanada, 9 Juli 2023. https://doi.org/10.18653/v1/2023.acl-long.880
Skitalinskaya, G., & Wachsmuth, H. (2023). To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (S. 15799–15816). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Band 1). https://doi.org/10.18653/v1/2023.acl-long.880
Skitalinskaya G, Wachsmuth H. To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support. in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023. S. 15799–15816. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/2023.acl-long.880
Skitalinskaya, Gabriella ; Wachsmuth, Henning. / To Revise or Not to Revise : Learning to Detect Improvable Claims for Argumentative Writing Support. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023. S. 15799–15816 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).
Download
@inproceedings{fbfe0aa2b9094c54a63d77d49c11d62a,
title = "To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support",
abstract = "Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In this work, we explore the main challenges to identifying argumentative claims in need of specific revisions. By learning from collaborative editing behaviors in online debates, we seek to capture implicit revision patterns in order to develop approaches aimed at guiding writers in how to further improve their arguments. We systematically compare the ability of common word embedding models to capture the differences between different versions of the same text, and we analyze their impact on various types of writing issues. To deal with the noisy nature of revision-based corpora, we propose a new sampling strategy based on revision distance. Opposed to approaches from prior work, such sampling can be done without employing additional annotations and judgments. Moreover, we provide evidence that using contextual information and domain knowledge can further improve prediction results. How useful a certain type of context is, depends on the issue the claim is suffering from, though.",
author = "Gabriella Skitalinskaya and Henning Wachsmuth",
note = "Funding Information: We thank Andreas Breiter for his valuable feedback on early drafts, and the anonymous reviewers for their helpful comments. This work was partially funded by the Deutsche Forschungsgemeinschaft(DFG, German Research Foundation) under project number 374666841, SFB 1342.; 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023, ACL 2023 ; Conference date: 09-07-2023 Through 14-07-2023",
year = "2023",
month = jul,
doi = "10.18653/v1/2023.acl-long.880",
language = "English",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
pages = "15799–15816",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",

}

Download

TY - GEN

T1 - To Revise or Not to Revise

T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023

AU - Skitalinskaya, Gabriella

AU - Wachsmuth, Henning

N1 - Funding Information: We thank Andreas Breiter for his valuable feedback on early drafts, and the anonymous reviewers for their helpful comments. This work was partially funded by the Deutsche Forschungsgemeinschaft(DFG, German Research Foundation) under project number 374666841, SFB 1342.

PY - 2023/7

Y1 - 2023/7

N2 - Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In this work, we explore the main challenges to identifying argumentative claims in need of specific revisions. By learning from collaborative editing behaviors in online debates, we seek to capture implicit revision patterns in order to develop approaches aimed at guiding writers in how to further improve their arguments. We systematically compare the ability of common word embedding models to capture the differences between different versions of the same text, and we analyze their impact on various types of writing issues. To deal with the noisy nature of revision-based corpora, we propose a new sampling strategy based on revision distance. Opposed to approaches from prior work, such sampling can be done without employing additional annotations and judgments. Moreover, we provide evidence that using contextual information and domain knowledge can further improve prediction results. How useful a certain type of context is, depends on the issue the claim is suffering from, though.

AB - Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In this work, we explore the main challenges to identifying argumentative claims in need of specific revisions. By learning from collaborative editing behaviors in online debates, we seek to capture implicit revision patterns in order to develop approaches aimed at guiding writers in how to further improve their arguments. We systematically compare the ability of common word embedding models to capture the differences between different versions of the same text, and we analyze their impact on various types of writing issues. To deal with the noisy nature of revision-based corpora, we propose a new sampling strategy based on revision distance. Opposed to approaches from prior work, such sampling can be done without employing additional annotations and judgments. Moreover, we provide evidence that using contextual information and domain knowledge can further improve prediction results. How useful a certain type of context is, depends on the issue the claim is suffering from, though.

UR - http://www.scopus.com/inward/record.url?scp=85174380849&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.acl-long.880

DO - 10.18653/v1/2023.acl-long.880

M3 - Conference contribution

AN - SCOPUS:85174380849

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 15799

EP - 15816

BT - Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Y2 - 9 July 2023 through 14 July 2023

ER -

Von denselben Autoren