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

Word embeddings are the standard model for semantic and syntacticrepresentations of words. Unfortunately, these models have been shown toexhibit undesirable word associations resulting from gender, racial, andreligious biases. Existing post-processing methods for debiasing wordembeddings are unable to mitigate gender bias hidden in the spatial arrangementof word vectors. In this paper, we propose RAN-Debias, a novel gender debiasingmethodology which not only eliminates the bias present in a word vector butalso alters the spatial distribution of its neighbouring vectors, achieving abias-free setting while maintaining minimal semantic offset. We also propose anew bias evaluation metric - Gender-based Illicit Proximity Estimate (GIPE),which measures the extent of undue proximity in word vectors resulting from thepresence of gender-based predilections. Experiments based on a suite ofevaluation metrics show that RAN-Debias significantly outperforms thestate-of-the-art in reducing proximity bias (GIPE) by at least 42.02%. It alsoreduces direct bias, adding minimal semantic disturbance, and achieves the bestperformance in a downstream application task (coreference resolution).

Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings