# Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution

arXiv: https://arxiv.org/abs/1905.08868 · HTML: https://mlsanity.com/paper/1905.08868/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2019.

## Built on by (most cited first, 4 of 4)

- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [NBIAS: A Natural Language Processing Framework for Bias Identification in Text](https://mlsanity.com/paper/2308.01681/) (2023)
- [RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution](https://mlsanity.com/paper/2309.04977/) (2023)
- [Detecting Hostile Posts using Relational Graph Convolutional Network](https://mlsanity.com/paper/2101.03485/) (2021)

## Abstract (arXiv)

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 2019 GAP Coreference Shared Task, and our codes are available online.