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

Language models such as Bidirectional Encoder Representations fromTransformers (BERT) have been very effective in various Natural LanguageProcessing (NLP) and text mining tasks including text classification. However,some tasks still pose challenges for these models, including textclassification with limited labels. This can result in a cold-start problem.Although some approaches have attempted to address this problem throughsingle-stage clustering as an intermediate training step coupled with apre-trained language model, which generates pseudo-labels to improveclassification, these methods are often error-prone due to the limitations ofthe clustering algorithms. To overcome this, we have developed a noveltwo-stage intermediate clustering with subsequent fine-tuning that models thepseudo-labels reliably, resulting in reduced prediction errors. The key noveltyin our model, IDoFew, is that the two-stage clustering coupled with twodifferent clustering algorithms helps exploit the advantages of thecomplementary algorithms that reduce the errors in generating reliablepseudo-labels for fine-tuning. Our approach has shown significant improvementscompared to strong comparative models.

IDoFew: Intermediate Training Using Dual-Clustering in Language Models for Few Labels Text Classification