Few-shot Named Entity Recognition (NER) aims to extract named entities using only a limited number of labeled examples. Existing contrastive learning methods often suffer from insufficient distinguishability in context vector representation because they either solely rely on label semantics or completely disregard them. To tackle this issue, we propose a unified label-aware token-level contrastive learning framework. Our approach enriches the context by utilizing label semantics as suffix prompts. Additionally, it simultaneously optimizes context-context and context-label contrastive learning objectives to enhance generalized discriminative contextual representations.Extensive experiments on various traditional test domains (OntoNotes, CoNLL'03, WNUT'17, GUM, I2B2) and the large-scale few-shot NER dataset (FEWNERD) demonstrate the effectiveness of our approach. It outperforms prior state-of-the-art models by a significant margin, achieving an average absolute gain of 7% in micro F1 scores across most scenarios. Further analysis reveals that our model benefits from its powerful transfer capability and improved contextual representations.

翻译：少样本命名实体识别旨在仅使用有限数量的标注样本来提取命名实体。现有的对比学习方法往往受限于上下文向量表示的可区分性不足，原因在于这些方法要么完全依赖标签语义，要么完全忽略标签语义。为解决这一问题，我们提出了一种统一的标签感知词级对比学习框架。该方法通过利用标签语义作为后缀提示来丰富上下文，同时联合优化上下文-上下文和上下文-标签对比学习目标，以增强具有泛化能力的判别性上下文表示。在多种传统测试领域（OntoNotes、CoNLL'03、WNUT'17、GUM、I2B2）以及大规模少样本NER数据集（FEWNERD）上的大量实验证明了我们方法的有效性。该方法显著超越了先前的最先进模型，在大多数场景下微平均F1分数平均绝对增益达到7%。进一步分析表明，我们的模型得益于其强大的迁移能力和改进的上下文表示。