@inproceedings{xu-yang-2019-look,
    title = "Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution",
    author = "Xu, Yinchuan  and
      Yang, Junlin",
    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/W19-3814/",
    doi = "10.18653/v1/W19-3814",
    pages = "96--101",
    abstract = "Gender bias has been found in existing coreference resolvers. In order to eliminate gender bias, a gender-balanced dataset Gendered Ambiguous Pronouns (GAP) has been released and the best baseline model achieves only 66.9{\%} F1. Bidirectional Encoder Representations from Transformers (BERT) has broken several NLP task records and can be used on GAP dataset. However, fine-tune BERT on a specific task is computationally expensive. In this paper, we propose an end-to-end resolver by combining pre-trained BERT with Relational Graph Convolutional Network (R-GCN). R-GCN is used for digesting structural syntactic information and learning better task-specific embeddings. Empirical results demonstrate that, under explicit syntactic supervision and without the need to fine tune BERT, R-GCN`s embeddings outperform the original BERT embeddings on the coreference task. Our work significantly improves the snippet-context baseline F1 score on GAP dataset from 66.9{\%} to 80.3{\%}. We participated in the Gender Bias for Natural Language Processing 2019 shared task, and our codes are available online."
}