@inproceedings{nguyen-ploeger-2025-need,
    title = "We Need to Measure Data Diversity in {NLP} {---} Better and Broader",
    author = "Nguyen, Dong  and
      Ploeger, Esther",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.445/",
    pages = "8823--8832",
    ISBN = "979-8-89176-332-6",
    abstract = "Although diversity in NLP datasets has received growing attention, the question of how to measure it remains largely underexplored. This opinion paper examines the conceptual and methodological challenges of measuring data diversity and argues that interdisciplinary perspectives are essential for developing more fine-grained and valid measures."
}