@inproceedings{howcroft-rieser-2021-happens,
    title = "What happens if you treat ordinal ratings as interval data? Human evaluations in {NLP} are even more under-powered than you think",
    author = "Howcroft, David M.  and
      Rieser, Verena",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.emnlp-main.703/",
    doi = "10.18653/v1/2021.emnlp-main.703",
    pages = "8932--8939"
}