@inproceedings{biblio8771424845634314387,
  author    = {Anya Belz and Craig Thomson and Ehud Reiter and Gavin Abercrombie and Jose M. Alonso-Moral and Mohammad Arvan and Jackie Cheung and Mark Cieliebak and Elizabeth Clark and Kees van Deemter and Tanvi Dinkar and Ondřej Dušek and Steffen Eger and Qixiang Fang and Albert Gatt and Dimitra Gkatzia and Javier González Corbelle and Dirk Hovy and Manuela Hürlimann and Takumi Ito and John D. Kelleher and Filip Klubička and Huiyuan Lai and Chris van der Lee and Emiel van Miltenburg and Yiru Li and Saad Mahamood and Margot Mieskes and Malvina Nissim and Natalie Parde and Ondřej Plátek and Verena Rieser and Pablo Mosteiro Romero and Joel Tetreault and Antonio Toral and Xiaojun Wan and Leo Wanner and Lewis Watson and Diyi Yang},
  year      = 2023,
  title     = {Missing information, unresponsive authors, experimental flaws: The impossibility of assessing the reproducibility of previous human evaluations in NLP},
  booktitle = {The Fourth Workshop on Insights from Negative Results in NLP: Proceedings of the Workshop},
  pages     = {1--10},
  publisher = {Association for Computational Linguistics},
  address   = {Stroudsburg, PA, USA},
  isbn      = {978-1-959429-49-4},
}