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

By Junlin Yang. 2019

22 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Su Lin Blodgett
  2. Hal Daumé Iii
  3. Hanna M. Wallach
  4. Solon Barocas
  5. Yejin Choi
  6. Noah A. Smith
  7. Yulia Tsvetkov
  8. Trevor Darrell

In Natural Language Processing

  1. Hal Daumé Iii
  2. Su Lin Blodgett
  3. Hanna M. Wallach
  4. Solon Barocas
  5. Yulia Tsvetkov
  6. Yejin Choi
  7. Emilio Ferrara
  8. Sunipa Dev

In Graph Learning

  1. Hal Daumé Iii
  2. Hanna M. Wallach
  3. Solon Barocas
  4. Su Lin Blodgett

Citations in the corpus