BERT for Coreference Resolution: Baselines and Analysis

Mandar Joshi, Omer Levy, Daniel S. Weld, Luke Zettlemoyer
8/24/2019
cs.CL

Official code: mandarjoshi90/coref (454 stars, Apache-2.0, last commit 2022-12-08).

Abstract

We apply BERT to coreference resolution, achieving strong improvements on the OntoNotes (+3.9 F1) and GAP (+11.5 F1) benchmarks. A qualitative analysis of model predictions indicates that, compared to ELMo and BERT-base, BERT-large is particularly better at distinguishing between related but distinct entities (e.g., President and CEO). However, there is still room for improvement in modeling document-level context, conversations, and mention paraphrasing. Our code and models are publicly available.

View on arXivView PDF

Code Implementations(1)

mandarjoshi90/corefOfficial100%
Apache-2.0

BERT for Coreference Resolution

45494C++, HTMLNov 9, 20183 years agoApache-2.0
bertcoreference-resolutionnaturalnlpspanbert

Cite this paper

@article{joshi2019bert,
  title  = {BERT for Coreference Resolution: Baselines and Analysis},
  author = {Mandar Joshi and Omer Levy and Daniel S. Weld and Luke Zettlemoyer},
  year   = {2019},
  eprint = {1908.09091},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1908.09091}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1908.09091.svg)](https://codeofpaper.com/paper/1908.09091)

Discussion