Improving Span Representation for Domain-adapted Coreference Resolution
This addresses the challenge of efficiently adapting coreference models to new domains like clinical notes, though it appears incremental as it builds on existing fine-tuning approaches.
The paper tackled the problem of requiring large annotated datasets for domain-adapted coreference resolution in clinical notes by incorporating concept knowledge to improve span representations, resulting in improved precision and F-1 scores on domain-specific spans.
Recent work has shown fine-tuning neural coreference models can produce strong performance when adapting to different domains. However, at the same time, this can require a large amount of annotated target examples. In this work, we focus on supervised domain adaptation for clinical notes, proposing the use of concept knowledge to more efficiently adapt coreference models to a new domain. We develop methods to improve the span representations via (1) a retrofitting loss to incentivize span representations to satisfy a knowledge-based distance function and (2) a scaffolding loss to guide the recovery of knowledge from the span representation. By integrating these losses, our model is able to improve our baseline precision and F-1 score. In particular, we show that incorporating knowledge with end-to-end coreference models results in better performance on the most challenging, domain-specific spans.