As the categories of named entities rapidly increase, the deployed NER models are required to keep updating toward recognizing more entity types, creating a demand for class-incremental learning for NER. Considering the privacy concerns and storage constraints, the standard paradigm for class-incremental NER updates the models with training data only annotated with the new classes, yet the entities from other entity classes are unlabeled, regarded as "Non-entity" (or "O"). In this work, we conduct an empirical study on the "Unlabeled Entity Problem" and find that it leads to severe confusion between "O" and entities, decreasing class discrimination of old classes and declining the model's ability to learn new classes. To solve the Unlabeled Entity Problem, we propose a novel representation learning method to learn discriminative representations for the entity classes and "O". Specifically, we propose an entity-aware contrastive learning method that adaptively detects entity clusters in "O". Furthermore, we propose two effective distance-based relabeling strategies for better learning the old classes. We introduce a more realistic and challenging benchmark for class-incremental NER, and the proposed method achieves up to 10.62\% improvement over the baseline methods.

翻译：随着命名实体类别迅速增加，已部署的NER模型需要持续更新以识别更多实体类型，这催生了NER的类增量学习需求。考虑到隐私顾虑和存储限制，类增量NER的标准范式仅使用标注有新类别的训练数据来更新模型，但来自其他实体类别的实体未被标注，被视为“非实体”（或“O”）。本研究对未标注实体问题进行了实证分析，发现该问题会导致“O”与实体之间的严重混淆，降低旧类别的区分能力，并削弱模型学习新类别的能力。为解决未标注实体问题，我们提出了一种新颖的表示学习方法，为实体类别和“O”学习判别性表示。具体而言，我们提出了一种实体感知对比学习方法，能自适应地检测“O”中的实体聚类。此外，我们提出了两种基于距离的有效重标注策略，以更好地学习旧类别。我们为类增量NER引入了一个更真实且更具挑战性的基准测试，所提方法较基线方法实现了最高10.62%的性能提升。