Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios
This work addresses data scarcity for researchers and practitioners in biomedical text mining by improving bioNER accuracy in low-resource settings, though it appears incremental as it builds on existing domain adaptation methods.
The paper tackled the problem of domain adaptation for biomedical named entity recognition (bioNER) in low-resource scenarios, where existing methods struggle with challenging linguistic characteristics in clinical narratives, and the proposed hardness-guided domain adaptation (HGDA) framework achieved significant performance improvement over the state-of-the-art MetaNER model on biomedical datasets.
Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic characteristics that clinical narratives possess, which leads to unsatisfactory performance. In this paper, we present a simple yet effective hardness-guided domain adaptation (HGDA) framework for bioNER tasks that can effectively leverage the domain hardness information to improve the adaptability of the learnt model in low-resource scenarios. Experimental results on biomedical datasets show that our model can achieve significant performance improvement over the recently published state-of-the-art (SOTA) MetaNER model