@inproceedings{wan-badillo-urquiola-2023-dragonfly,
    title = "Dragonfly{\_}captain at {S}em{E}val-2023 Task 11: Unpacking Disagreement with Investigation of Annotator Demographics and Task Difficulty",
    author = "Wan, Ruyuan  and
      Badillo-Urquiola, Karla",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2023.semeval-1.272/",
    doi = "10.18653/v1/2023.semeval-1.272",
    pages = "1978--1982",
    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."
}