Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Most existing prototype-based sequence labeling models tend to memorize entity mentions which would be easily confused by close prototypes. In this paper, we proposed a Prototypical Semantic Decoupling method via joint Contrastive learning (PSDC) for few-shot NER. Specifically, we decouple class-specific prototypes and contextual semantic prototypes by two masking strategies to lead the model to focus on two different semantic information for inference. Besides, we further introduce joint contrastive learning objectives to better integrate two kinds of decoupling information and prevent semantic collapse. Experimental results on two few-shot NER benchmarks demonstrate that PSDC consistently outperforms the previous SOTA methods in terms of overall performance. Extensive analysis further validates the effectiveness and generalization of PSDC.

翻译：多数现有的原型序列标签模型倾向于将实体提到很容易被接近的原型混为一谈。在本文件中,我们建议通过联合竞争学习(PSDC),为少见的NER采用一种原型语义脱钩方法。具体地说,我们通过两个掩码战略,将特定类原型和背景语义原型脱钩,使模型侧重于两种不同的语义信息,以便推断。此外,我们进一步引入了对比式的联合学习目标,以更好地整合两种脱钩信息并防止语义崩溃。两个微小的NER基准的实验结果表明,FDC在总体业绩方面始终超越了以前的SOTA方法。广泛的分析进一步验证了SCDC的有效性和普遍性。</s>