@inproceedings{vania-etal-2021-comparing,
    title = "Comparing Test Sets with Item Response Theory",
    author = "Vania, Clara  and
      Htut, Phu Mon  and
      Huang, William  and
      Mungra, Dhara  and
      Pang, Richard Yuanzhe  and
      Phang, Jason  and
      Liu, Haokun  and
      Cho, Kyunghyun  and
      Bowman, Samuel R.",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.acl-long.92/",
    doi = "10.18653/v1/2021.acl-long.92",
    pages = "1141--1158"
}