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

The prevalence of abusive language on different online platforms has been amajor concern that raises the need for automated cross-platform abusivelanguage detection. However, prior works focus on concatenating data frommultiple platforms, inherently adopting Empirical Risk Minimization (ERM)method. In this work, we address this challenge from the perspective of domaingeneralization objective. We design SCL-Fish, a supervised contrastive learningintegrated meta-learning algorithm to detect abusive language on unseenplatforms. Our experimental analysis shows that SCL-Fish achieves betterperformance over ERM and the existing state-of-the-art models. We also showthat SCL-Fish is data-efficient and achieves comparable performance with thelarge-scale pre-trained models upon finetuning for the abusive languagedetection task.

Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning