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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Prompting methods have shown impressive performance in a variety of textmining tasks and applications, especially few-shot ones. Despite the promisingprospects, the performance of prompting model largely depends on the design ofprompt template and verbalizer. In this work, we propose MetricPrompt, whicheases verbalizer design difficulty by reformulating few-shot textclassification task into text pair relevance estimation task. MetricPromptadopts prompting model as the relevance metric, further bridging the gapbetween Pre-trained Language Model's (PLM) pre-training objective and textclassification task, making possible PLM's smooth adaption. Taking a trainingsample and a query one simultaneously, MetricPrompt captures cross-samplerelevance information for accurate relevance estimation. We conduct experimentson three widely used text classification datasets across four few-shotsettings. Results show that MetricPrompt outperforms manual verbalizer andother automatic verbalizer design methods across all few-shot settings,achieving new state-of-the-art (SOTA) performance.

MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text Classification