Advanced search
1 file | 927.21 KB Add to list

Combining Language Models and Linguistic Information to Label Entities in Memes

Pranaydeep Singh (UGent) , Aaron Maladry (UGent) and Els Lefever (UGent)
Author
Organization
Abstract
This paper describes the system we developed for the shared task “Hero, Villain and Victim: Dissecting harmful memes for Semantic role labeling of entities” organized in the frame- work of the Second Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation (Constraint 2022). We present an ensemble approach combining transformer-based models and linguistic information, such as the presence of irony and implicit sentiment associated to the target named entities. The ensemble system obtains promising classification scores, with a macro F-score of 55%, resulting in a third place finish in the competition.
Keywords
LT3

Downloads

  • 2022.constraint-1.5.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 927.21 KB

Citation

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

MLA
Singh, Pranaydeep, et al. “Combining Language Models and Linguistic Information to Label Entities in Memes.” Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, Association for Computational Linguistics, 2022, pp. 35–42.
APA
Singh, P., Maladry, A., & Lefever, E. (2022). Combining Language Models and Linguistic Information to Label Entities in Memes. Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, 35–42. Dublin, Ireland: Association for Computational Linguistics.
Chicago author-date
Singh, Pranaydeep, Aaron Maladry, and Els Lefever. 2022. “Combining Language Models and Linguistic Information to Label Entities in Memes.” In Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, 35–42. Dublin, Ireland: Association for Computational Linguistics.
Chicago author-date (all authors)
Singh, Pranaydeep, Aaron Maladry, and Els Lefever. 2022. “Combining Language Models and Linguistic Information to Label Entities in Memes.” In Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, 35–42. Dublin, Ireland: Association for Computational Linguistics.
Vancouver
1.
Singh P, Maladry A, Lefever E. Combining Language Models and Linguistic Information to Label Entities in Memes. In: Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations. Dublin, Ireland: Association for Computational Linguistics; 2022. p. 35–42.
IEEE
[1]
P. Singh, A. Maladry, and E. Lefever, “Combining Language Models and Linguistic Information to Label Entities in Memes,” in Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, Dublin, Ireland, 2022, pp. 35–42.
@inproceedings{8753104,
  abstract     = {{This paper describes the system we developed for the shared task “Hero, Villain and Victim: Dissecting harmful memes for Semantic role labeling of entities” organized in the frame- work of the Second Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation (Constraint 2022). We present an ensemble approach combining transformer-based models and linguistic information, such as the presence of irony and implicit sentiment associated to the target named entities. The ensemble system obtains promising classification scores, with a macro F-score of 55%, resulting in a third place finish in the competition.}},
  author       = {{Singh, Pranaydeep and Maladry, Aaron and Lefever, Els}},
  booktitle    = {{Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations}},
  isbn         = {{978-1-955917-31-5}},
  keywords     = {{LT3}},
  language     = {{eng}},
  location     = {{Dublin, Ireland}},
  pages        = {{35--42}},
  publisher    = {{Association for Computational Linguistics}},
  title        = {{Combining Language Models and Linguistic Information to Label Entities in Memes}},
  year         = {{2022}},
}