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

Natural language generation models reproduce and often amplify the biasespresent in their training data. Previous research explored usingsequence-to-sequence rewriting models to transform biased model outputs (ororiginal texts) into more gender-fair language by creating pseudo training datathrough linguistic rules. However, this approach is not practical for languageswith more complex morphology than English. We hypothesise that creatingtraining data in the reverse direction, i.e. starting from gender-fair text, iseasier for morphologically complex languages and show that it matches theperformance of state-of-the-art rewriting models for English. To eliminate therule-based nature of data creation, we instead propose using machinetranslation models to create gender-biased text from real gender-fair text viaround-trip translation. Our approach allows us to train a rewriting model forGerman without the need for elaborate handcrafted rules. The outputs of thismodel increased gender-fairness as shown in a human evaluation study.

Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model