Papers › Gendered Pronoun Resolution using BERT and an extractive question answering formulation

Gendered Pronoun Resolution using BERT and an extractive question answering formulation

9 Jun 2019WS 2019 8arXiv:1906.03695archive 2025-07-28

Rakesh Chada

The resolution of ambiguous pronouns is a longstanding challenge in Natural Language Understanding. Recent studies have suggested gender bias among state-of-the-art coreference resolution systems. As an example, Google AI Language team recently released a gender-balanced dataset and showed that performance of these coreference resolvers is significantly limited on the dataset. In this paper, we propose an extractive question answering (QA) formulation of pronoun resolution task that overcomes this limitation and shows much lower gender bias (0.99) on their dataset. This system uses fine-tuned representations from the pre-trained BERT model and outperforms the existing baseline by a significant margin (22.2% absolute improvement in F1 score) without using any hand-engineered features. This QA framework is equally performant even without the knowledge of the candidate antecedents of the pronoun. An ensemble of QA and BERT-based multiple choice and sequence classification models further improves the F1 (23.3% absolute improvement upon the baseline). This ensemble model was submitted to the shared task for the 1st ACL workshop on Gender Bias for Natural Language Processing. It ranked 9th on the final official leaderboard. Source code is available at https://github.com/rakeshchada/corefqa

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

rakeshchada/corefqa officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Coreference Resolution Extractive Question-Answering Multiple-choice Natural Language Understanding Question Answering coreference-resolution

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Coreference Resolution	GAP	Full Ensemble	Bias (F/M)	0.98	#4 of 5	Archive leaderboard	report
Coreference Resolution	GAP	Full Ensemble	Feminine F1 (F)	89.5	#4 of 5	Archive leaderboard	report
Coreference Resolution	GAP	Full Ensemble	Masculine F1 (M)	90.9	#4 of 5	Archive leaderboard	report
Coreference Resolution	GAP	Full Ensemble	Overall F1	90.2	#4 of 5	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections