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) is a task aiming to identify namedentities via limited annotated samples. Recently, prototypical networks haveshown promising performance in few-shot NER. Most of prototypical networks willutilize the entities from the support set to construct label prototypes and usethe query set to compute span-level similarities and optimize these labelprototype representations. However, these methods are usually unsuitable forfine-tuning in the target domain, where only the support set is available. Inthis paper, we propose PromptNER: a novel prompting method for few-shot NER viak nearest neighbor search. We use prompts that contains entity categoryinformation to construct label prototypes, which enables our model to fine-tunewith only the support set. Our approach achieves excellent transfer learningability, and extensive experiments on the Few-NERD and CrossNER datasetsdemonstrate that our model achieves superior performance over state-of-the-artmethods.

PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search