Distantly-Supervised Named Entity Recognition effectively alleviates the burden of time-consuming and expensive annotation in the supervised setting. But the context-free matching process and the limited coverage of knowledge bases introduce inaccurate and incomplete annotation noise respectively. Previous studies either considered only incomplete annotation noise or indiscriminately handle two types of noise with the same strategy. In this paper, we argue that the different causes of two types of noise bring up the requirement of different strategies in model architecture. Therefore, we propose the SANTA to handle these two types of noise separately with (1) Memory-smoothed Focal Loss and Entity-aware KNN to relieve the entity ambiguity problem caused by inaccurate annotation, and (2) Boundary Mixup to alleviate decision boundary shifting problem caused by incomplete annotation and a noise-tolerant loss to improve the robustness. Benefiting from our separate tailored strategies, we confirm in the experiment that the two types of noise are well mitigated. SANTA also achieves a new state-of-the-art on five public datasets.

本篇论文提出了一个新的名词实体识别模型 SANTA，其使用 Memory-smoothed Focal Loss 和 Entity-aware KNN 分别处理精度不准确和不完整噪音引起的实体模糊问题，使用 Boundary Mixup 和一种噪音容错的 loss 来缓解决策边界问题和提高模型的稳健性，实验结果表明 SANTA 可以有效缓解两种噪声类型，并在五个公共数据集上达到了新的最优表现。

SANTA：针对远程监督命名实体识别中的注释噪声和不完整策略的分离