BERT for Coreference Resolution: Baselines and Analysis
This work addresses coreference resolution for natural language processing, but it is incremental as it applies an existing method to a specific task.
The paper tackled coreference resolution by applying BERT, achieving improvements of +3.9 F1 on OntoNotes and +11.5 F1 on GAP benchmarks.
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.