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

Warning: this paper contains content that may be offensive or upsetting.  Numerous natural language processing models have tried injecting commonsenseby using the ConceptNet knowledge base to improve performance on differenttasks. ConceptNet, however, is mostly crowdsourced from humans and may reflecthuman biases such as "lawyers are dishonest." It is important that these biasesare not conflated with the notion of commonsense. We study this missing yetimportant problem by first defining and quantifying biases in ConceptNet as twotypes of representational harms: overgeneralization of polarized perceptionsand representation disparity. We find that ConceptNet contains severe biasesand disparities across four demographic categories. In addition, we analyze twodownstream models that use ConceptNet as a source for commonsense knowledge andfind the existence of biases in those models as well. We further propose afiltered-based bias-mitigation approach and examine its effectiveness. We showthat our mitigation approach can reduce the issues in both resource and modelsbut leads to a performance drop, leaving room for future work to build fairerand stronger commonsense models.

Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources