@inproceedings{onderkova-etal-2025-reprohum,
    title = "{R}epro{H}um {\#}0669-08: Reproducing Sentiment Transfer Evaluation",
    author = "Onderkov{\'a}, Krist{\'y}na  and
      Lango, Mateusz  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Dusek, Ondrej",
    editor = "Dhole, Kaustubh  and
      Clinciu, Miruna",
    booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
    month = jul,
    year = "2025",
    address = "Vienna, Austria and virtual meeting",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.gem-1.55/",
    pages = "601--608",
    ISBN = "979-8-89176-261-9",
    abstract = "We describe a reproduction of a human annotation experiment that was performed to evaluate the effectiveness of text style transfer systems (Reif et al., 2021). Despite our efforts to closely imitate the conditions of the original study, the results obtained differ significantly from those in the original study. We performed a statistical analysis of the results obtained, discussed the sources of these discrepancies in the study design, and quantified reproducibility. The reproduction followed the common approach to reproduction adopted by the ReproHum project."
}