@inproceedings{nahurna-romanyshyn-2025-gender,
    title = "Gender Swapping as a Data Augmentation Technique: Developing Gender-Balanced Datasets for {U}krainian Language Processing",
    author = "Nahurna, Olha  and
      Romanyshyn, Mariana",
    editor = "Romanyshyn, Mariana",
    booktitle = "Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.unlp-1.16/",
    pages = "147--161",
    ISBN = "979-8-89176-269-5",
    abstract = "This paper presents a pipeline for generating gender-balanced datasets through sentence-level gender swapping, addressing the gender-imbalance issue in Ukrainian texts. We select sentences with gender-marked entities, focusing on job titles, generate their inverted alternatives using LLMs and human-in-the-loop, and fine-tune Aya-101 on the resulting dataset for the task of gender swapping. Additionally, we train a Named Entity Recognition (NER) model on gender-balanced data, demonstrating its ability to better recognize gendered entities. The findings unveil the potential of gender-balanced datasets to enhance model robustness and support more fair language processing. Finally, we make a gender-swapped version of NER-UK{\textasciitilde}2.0 and the fine-tuned Aya-101 model available for download and further research."
}