@inproceedings{mccoy-etal-2020-berts,
    title = "{BERT}s of a feather do not generalize together: Large variability in generalization across models with similar test set performance",
    author = "McCoy, R. Thomas  and
      Min, Junghyun  and
      Linzen, Tal",
    editor = "Alishahi, Afra  and
      Belinkov, Yonatan  and
      Chrupa{\l}a, Grzegorz  and
      Hupkes, Dieuwke  and
      Pinter, Yuval  and
      Sajjad, Hassan",
    booktitle = "Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.blackboxnlp-1.21/",
    doi = "10.18653/v1/2020.blackboxnlp-1.21",
    pages = "217--227"
}