@article{jiang-de-marneffe-2021-thinks,
    title = "He Thinks He Knows Better than the Doctors: {BERT} for Event Factuality Fails on Pragmatics",
    author = "Jiang, Nanjiang  and
      de Marneffe, Marie-Catherine",
    editor = "Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "9",
    year = "2021",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2021.tacl-1.64/",
    doi = "10.1162/tacl_a_00414",
    pages = "1081--1097",
    abstract = "We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Contrary to what the high performance suggests, we are still far from having a robust system for factuality prediction."
}