BERT for Coreference Resolution: Baselines and Analysis

08/24/2019
by   Mandar Joshi, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset