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

Debiasing word embeddings has been largely limited to individual andindependent social categories. However, real-world corpora typically presentmultiple social categories that possibly correlate or intersect with eachother. For instance, "hair weaves" is stereotypically associated with AfricanAmerican females, but neither African American nor females alone. Therefore,this work studies biases associated with multiple social categories: jointbiases induced by the union of different categories and intersectional biasesthat do not overlap with the biases of the constituent categories. We firstempirically observe that individual biases intersect non-trivially (i.e., overa one-dimensional subspace). Drawing from the intersectional theory in socialscience and the linguistic theory, we then construct an intersectional subspaceto debias for multiple social categories using the nonlinear geometry ofindividual biases. Empirical evaluations corroborate the efficacy of ourapproach. Data and implementation code can be downloaded athttps://github.com/GitHubLuCheng/Implementation-of-JoSEC-COLING-22.

Debiasing Word Embeddings with Nonlinear Geometry