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

Prompt tuning (PT) is an effective approach to adapting pre-trained languagemodels to downstream tasks. Without a good initialization, prompt tuningdoesn't perform well under few-shot settings. So pre-trained prompt tuning(PPT) is proposed to initialize prompts by leveraging pre-training data. Wepropose MetaPT (Meta-learned Prompt Tuning) to further improve PPT'sinitialization by considering latent structure within the pre-training data.Specifically, we introduce the structure by first clustering pre-training datainto different auxiliary tasks with unsupervised methods. Then we use thesetasks to pre-train prompts with a meta-learning algorithm. Such a process canmake prompts learn a better initialization by discovering commonalities amongthese auxiliary tasks. We evaluate our method on seven downstream tasks. OurMetaPT achieves better and more stable performance than the state-of-the-artmethod.

Learning a Better Initialization for Soft Prompts via Meta-Learning