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

A common limitation of diagnostic tests for detecting social biases in NLPmodels is that they may only detect stereotypic associations that arepre-specified by the designer of the test. Since enumerating all possibleproblematic associations is infeasible, it is likely these tests fail to detectbiases that are present in a model but not pre-specified by the designer. Toaddress this limitation, we propose SODAPOP (SOcial bias Discovery from Answersabout PeOPle) in social commonsense question-answering. Our pipeline generatesmodified instances from the Social IQa dataset (Sap et al., 2019) by (1)substituting names associated with different demographic groups, and (2)generating many distractor answers from a masked language model. By using asocial commonsense model to score the generated distractors, we are able touncover the model's stereotypic associations between demographic groups and anopen set of words. We also test SODAPOP on debiased models and show thelimitations of multiple state-of-the-art debiasing algorithms.

SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models