Advanced search
1 file | 444.18 KB Add to list

Stance-aware definition generation for argumentative texts

Natalia Evgrafova (UGent) , Loic De Langhe (UGent) , Veronique Hoste (UGent) and Els Lefever (UGent)
Author
Organization
Abstract
Definition generation models trained on dictionary data are generally expected to produce neutral and unbiased output while capturing the contextual nuances. However, previous studies have shown that generated definitions can inherit biases from both the underlying models and the input context. This paper examines the extent to which stance-related bias in argumentative data influences the generated definitions. In particular, we train a model on a slang-based dictionary to explore the feasibility of generating persuasive definitions that concisely reflect opposing parties' understandings of contested terms. Through this study, we provide new insights into bias propagation in definition generation and its implications for definition generation applications and argument mining.

Downloads

  • Definitions paper acl.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 444.18 KB

Citation

Please use this url to cite or link to this publication:

MLA
Evgrafova, Natalia, et al. “Stance-Aware Definition Generation for Argumentative Texts.” PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP, edited by Elena Chistova et al., Association for Computational Linguistics (ACL), 2025, pp. 168–80, doi:10.18653/v1/2025.argmining-1.16.
APA
Evgrafova, N., De Langhe, L., Hoste, V., & Lefever, E. (2025). Stance-aware definition generation for argumentative texts. In E. Chistova, P. Cimiano, S. Haddadan, G. Lapesa, & R. Ruiz-Dolz (Eds.), PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP (pp. 168–180). https://doi.org/10.18653/v1/2025.argmining-1.16
Chicago author-date
Evgrafova, Natalia, Loic De Langhe, Veronique Hoste, and Els Lefever. 2025. “Stance-Aware Definition Generation for Argumentative Texts.” In PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP, edited by Elena Chistova, Philipp Cimiano, Shohreh Haddadan, Gabriella Lapesa, and Ramon Ruiz-Dolz, 168–80. Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2025.argmining-1.16.
Chicago author-date (all authors)
Evgrafova, Natalia, Loic De Langhe, Veronique Hoste, and Els Lefever. 2025. “Stance-Aware Definition Generation for Argumentative Texts.” In PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP, ed by. Elena Chistova, Philipp Cimiano, Shohreh Haddadan, Gabriella Lapesa, and Ramon Ruiz-Dolz, 168–180. Association for Computational Linguistics (ACL). doi:10.18653/v1/2025.argmining-1.16.
Vancouver
1.
Evgrafova N, De Langhe L, Hoste V, Lefever E. Stance-aware definition generation for argumentative texts. In: Chistova E, Cimiano P, Haddadan S, Lapesa G, Ruiz-Dolz R, editors. PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP. Association for Computational Linguistics (ACL); 2025. p. 168–80.
IEEE
[1]
N. Evgrafova, L. De Langhe, V. Hoste, and E. Lefever, “Stance-aware definition generation for argumentative texts,” in PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP, Vienna, AUSTRIA, 2025, pp. 168–180.
@inproceedings{01K3NCBXPSW194SNX8ECJ2SK8K,
  abstract     = {{Definition generation models trained on dictionary data are generally expected to produce neutral and unbiased output while capturing the contextual nuances. However, previous studies have shown that generated definitions can inherit biases from both the underlying models and the input context. This paper examines the extent to which stance-related bias in argumentative data influences the generated definitions. In particular, we train a model on a slang-based dictionary to explore the feasibility of generating persuasive definitions that concisely reflect opposing parties' understandings of contested terms. Through this study, we provide new insights into bias propagation in definition generation and its implications for definition generation applications and argument mining.}},
  author       = {{Evgrafova, Natalia and De Langhe, Loic and Hoste, Veronique and Lefever, Els}},
  booktitle    = {{PROCEEDINGS OF THE 12TH ARGUMENT MINING WORKSHOP}},
  editor       = {{Chistova, Elena and Cimiano, Philipp and Haddadan, Shohreh and Lapesa, Gabriella and Ruiz-Dolz, Ramon}},
  isbn         = {{9798891762589}},
  language     = {{eng}},
  location     = {{Vienna, AUSTRIA}},
  pages        = {{168--180}},
  publisher    = {{Association for Computational Linguistics (ACL)}},
  title        = {{Stance-aware definition generation for argumentative texts}},
  url          = {{http://doi.org/10.18653/v1/2025.argmining-1.16}},
  year         = {{2025}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: