CLMay 21, 2019

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

arXiv:1905.08868v31097 citations
Originality Incremental advance
AI Analysis

This work addresses gender bias in NLP for coreference resolution, offering a significant but incremental improvement over existing methods.

The paper tackled gender bias in coreference resolution by proposing a model combining pre-trained BERT with Relational Graph Convolutional Network (R-GCN) to improve performance on the Gendered Ambiguous Pronouns (GAP) dataset, achieving an F1 score increase from 66.9% to 80.3%.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes