Dragonfly_captain at SemEval-2023 Task 11: Unpacking Disagreement with Investigation of Annotator Demographics and Task Difficulty

Ruyuan Wan, Karla Badillo-Urquiola


Abstract
This study investigates learning with disagreement in NLP tasks and evaluates its performance on four datasets. The results suggest that the model performs best on the experimental dataset and faces challenges in minority languages. Furthermore, the analysis indicates that annotator demographics play a significant role in the interpretation of such tasks. This study suggests the need for greater consideration of demographic differences in annotators and more comprehensive evaluation metrics for NLP models.
Anthology ID:
2023.semeval-1.272
Volume:
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1978–1982
Language:
URL:
https://aclanthology.org/2023.semeval-1.272
DOI:
10.18653/v1/2023.semeval-1.272
Bibkey:
Cite (ACL):
Ruyuan Wan and Karla Badillo-Urquiola. 2023. Dragonfly_captain at SemEval-2023 Task 11: Unpacking Disagreement with Investigation of Annotator Demographics and Task Difficulty. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1978–1982, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Dragonfly_captain at SemEval-2023 Task 11: Unpacking Disagreement with Investigation of Annotator Demographics and Task Difficulty (Wan & Badillo-Urquiola, SemEval 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.semeval-1.272.pdf