E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition
This addresses the need for trustworthy NER in open environments, offering an incremental improvement by adapting evidential deep learning to NER-specific challenges.
The paper tackled the problem of quantifying uncertainty in named entity recognition (NER) systems, which is often ignored, by proposing E-NER, a framework that improves uncertainty estimation and achieves better OOV/OOD detection and generalization on OOV entities compared to state-of-the-art baselines.
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments. Evidential deep learning (EDL) has recently been proposed as a promising solution to explicitly model predictive uncertainty for classification tasks. However, directly applying EDL to NER applications faces two challenges, i.e., the problems of sparse entities and OOV/OOD entities in NER tasks. To address these challenges, we propose a trustworthy NER framework named E-NER by introducing two uncertainty-guided loss terms to the conventional EDL, along with a series of uncertainty-guided training strategies. Experiments show that E-NER can be applied to multiple NER paradigms to obtain accurate uncertainty estimation. Furthermore, compared to state-of-the-art baselines, the proposed method achieves a better OOV/OOD detection performance and better generalization ability on OOV entities.