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 have recently been shown to reflect many of the pronouncedsocietal biases (e.g., gender bias or racial bias). Existing studies are,however, limited in scope and do not investigate the consistency of biasesacross relevant dimensions like embedding models, types of texts, and differentlanguages. In this work, we present a systematic study of biases encoded indistributional word vector spaces: we analyze how consistent the bias effectsare across languages, corpora, and embedding models. Furthermore, we analyzethe cross-lingual biases encoded in bilingual embedding spaces, indicative ofthe effects of bias transfer encompassed in cross-lingual transfer of NLPmodels. Our study yields some unexpected findings, e.g., that biases can beemphasized or downplayed by different embedding models or that user-generatedcontent may be less biased than encyclopedic text. We hope our work catalyzesbias research in NLP and informs the development of bias reduction techniques.

Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors