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

Most NER methods rely on extensive labeled data for model training, whichstruggles in the low-resource scenarios with limited training data. Existingdominant approaches usually suffer from the challenge that the target domainhas different label sets compared with a resource-rich source domain, which canbe concluded as class transfer and domain transfer. In this paper, we propose alightweight tuning paradigm for low-resource NER via pluggable prompting(LightNER). Specifically, we construct the unified learnable verbalizer ofentity categories to generate the entity span sequence and entity categorieswithout any label-specific classifiers, thus addressing the class transferissue. We further propose a pluggable guidance module by incorporatinglearnable parameters into the self-attention layer as guidance, which canre-modulate the attention and adapt pre-trained weights. Note that we only tunethose inserted module with the whole parameter of the pre-trained languagemodel fixed, thus, making our approach lightweight and flexible forlow-resource scenarios and can better transfer knowledge across domains.Experimental results show that LightNER can obtain comparable performance inthe standard supervised setting and outperform strong baselines in low-resourcesettings. Code is inhttps://github.com/zjunlp/DeepKE/tree/main/example/ner/few-shot.

LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting