Кемсітушілікті азайту

AbstractThis paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is …...

AbstractOnline misogyny, a category of online abusive language, has serious and harmful social consequences. Automatic detection of misogynistic language online, while imperative, poses complicated challenges to both data gathering, data …...

Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. Sep- arately, certified …...

AbstractText representation models are prone to exhibit a range of societal biases, reflecting the non-controlled and biased nature of the underlying pretraining data, which consequently leads to severe ethical issues …...

AbstractAutomatic language processing is used frequently in the Human Resources (HR) sector for automated candidate sourcing and evaluation of resumes. These models often use pre-trained language models where it is …...

AbstractDatasets with significant proportions of bias present threats for training a trustworthy model on NLU tasks. Despite yielding great progress, current debiasing methods impose excessive reliance on the knowledge of …...

AbstractDespite their promising results on standard benchmarks, NLU models are still prone to make predictions based on shortcuts caused by unintended bias in the dataset. For example, an NLI model …...