@inproceedings{belz-etal-2023-non, title = "Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in {NLP}", author = "Belz, Anya and Thomson, Craig and Reiter, Ehud and Mille, Simon", editor = "Rogers, Anna and Boyd-Graber, Jordan and Okazaki, Naoaki", booktitle = "Findings of the Association for Computational Linguistics: ACL 2023", month = jul, year = "2023", address = "Toronto, Canada", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.findings-acl.226/", doi = "10.18653/v1/2023.findings-acl.226", pages = "3676--3687" }