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

Written language carries explicit and implicit biases that can distract frommeaningful signals. For example, letters of reference may describe male andfemale candidates differently, or their writing style may indirectly revealdemographic characteristics. At best, such biases distract from the meaningfulcontent of the text; at worst they can lead to unfair outcomes. We investigatethe challenge of re-generating input sentences to 'neutralize' sensitiveattributes while maintaining the semantic meaning of the original text (e.g. isthe candidate qualified?). We propose a gradient-based rewriting framework,Detect and Perturb to Neutralize (DEPEN), that first detects sensitivecomponents and masks them for regeneration, then perturbs the generation modelat decoding time under a neutralizing constraint that pushes the (predicted)distribution of sensitive attributes towards a uniform distribution. Ourexperiments in two different scenarios show that DEPEN can regenerate fluentalternatives that are neutral in the sensitive attribute while maintaining thesemantics of other attributes.

Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding