English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition