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/

Zendy Plus

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

Zendy Tools

Zendy Open

Algorithmic bias often arises as a result of differential subgroup validity,in which predictive relationships vary across groups. For example, in toxiclanguage detection, comments targeting different demographic groups can varymarkedly across groups. In such settings, trained models can be dominated bythe relationships that best fit the majority group, leading to disparateperformance. We propose framing toxicity detection as multi-task learning(MTL), allowing a model to specialize on the relationships that are relevant toeach demographic group while also leveraging shared properties across groups.With toxicity detection, each task corresponds to identifying toxicity againsta particular demographic group. However, traditional MTL requires labels forall tasks to be present for every data point. To address this, we proposeConditional MTL (CondMTL), wherein only training examples relevant to the givendemographic group are considered by the loss function. This lets us learn groupspecific representations in each branch which are not cross contaminated byirrelevant labels. Results on synthetic and real data show that using CondMTLimproves predictive recall over various baselines in general and for theminority demographic group in particular, while having similar overallaccuracy.

Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection