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

Toxicity has become a grave problem for many online communities and has beengrowing across many languages, including Russian. Hate speech creates anenvironment of intimidation, discrimination, and may even incite somereal-world violence. Both researchers and social platforms have been focused ondeveloping models to detect toxicity in online communication for a while now. Acommon problem of these models is the presence of bias towards some words (e.g.woman, black, jew) that are not toxic, but serve as triggers for the classifierdue to model caveats. In this paper, we describe our efforts towardsclassifying hate speech in Russian, and propose simple techniques of reducingunintended bias, such as generating training data with language models usingterms and words related to protected identities as context and applying worddropout to such words.

Reducing Unintended Identity Bias in Russian Hate Speech Detection