@inproceedings{yang-etal-2019-fill,
    title = "Fill the {GAP}: Exploiting {BERT} for Pronoun Resolution",
    author = "Yang, Kai-Chou  and
      Niven, Timothy  and
      Chou, Tzu Hsuan  and
      Kao, Hung-Yu",
    editor = "Costa-juss{\`a}, Marta R.  and
      Hardmeier, Christian  and
      Radford, Will  and
      Webster, Kellie",
    booktitle = "Proceedings of the First Workshop on Gender Bias in Natural Language Processing",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W19-3815/",
    doi = "10.18653/v1/W19-3815",
    pages = "102--106",
    abstract = "In this paper, we describe our entry in the gendered pronoun resolution competition which achieved fourth place without data augmentation. Our method is an ensemble system of BERTs which resolves co-reference in an interaction space. We report four insights from our work: BERT`s representations involve significant redundancy; modeling interaction effects similar to natural language inference models is useful for this task; there is an optimal BERT layer to extract representations for pronoun resolution; and the difference between the attention weights from the pronoun to the candidate entities was highly correlated with the correct label, with interesting implications for future work."
}