A Protypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition

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 and contextual semantic prototypes by two masking strategies to guide the model 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 the 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 analyses further validate the effectiveness and generalization of PSDC.