# Resolving Gendered Ambiguous Pronouns with BERT

## TL;DR

This paper presents a BERT-based method for gender-balanced pronoun resolution, significantly improving accuracy and reducing gender bias in coreference resolution tasks.

## Contribution

The authors develop a BERT-based approach that achieves high accuracy and reduces gender bias in resolving ambiguous gendered pronouns.

## Key findings

- Achieved 92% F1 score on benchmark dataset
- Reduced gender bias compared to previous models
- Demonstrated effectiveness of BERT in coreference resolution

## Abstract

Pronoun resolution is part of coreference resolution, the task of pairing an expression to its referring entity. This is an important task for natural language understanding and a necessary component of machine translation systems, chat bots and assistants. Neural machine learning systems perform far from ideally in this task, reaching as low as 73% F1 scores on modern benchmark datasets. Moreover, they tend to perform better for masculine pronouns than for feminine ones. Thus, the problem is both challenging and important for NLP researchers and practitioners. In this project, we describe our BERT-based approach to solving the problem of gender-balanced pronoun resolution. We are able to reach 92% F1 score and a much lower gender bias on the benchmark dataset shared by Google AI Language team.