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

Text classification is essential for organizing unstructured text.Traditional methods rely on human annotations or, more recently, a set of classseed words for supervision, which can be costly, particularly for specializedor emerging domains. To address this, using class surface names alone asextremely weak supervision has been proposed. However, existing approachestreat different levels of text granularity (documents, sentences, or words)independently, disregarding inter-granularity class disagreements and thecontext identifiable exclusively through joint extraction. In order to tacklethese issues, we introduce MEGClass, an extremely weakly-supervised textclassification method that leverages Mutually-Enhancing Text Granularities.MEGClass utilizes coarse- and fine-grained context signals obtained by jointlyconsidering a document's most class-indicative words and sentences. Thisapproach enables the learning of a contextualized document representation thatcaptures the most discriminative class indicators. By preserving theheterogeneity of potential classes, MEGClass can select the most informativeclass-indicative documents as iterative feedback to enhance the initialword-based class representations and ultimately fine-tune a pre-trained textclassifier. Extensive experiments on seven benchmark datasets demonstrate thatMEGClass outperforms other weakly and extremely weakly supervised methods.

MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities