Защищенные атрибуты

AbstractElazar and Goldberg (2018) showed that protected attributes can be extracted from the representations of a debiased neural network for mention detection at above-chance levels, by evaluating a diagnostic classifier …...

AbstractMost NLP datasets are not annotated with protected attributes such as gender, making it difficult to measure classification bias using standard measures of fairness (e.g., equal opportunity). However, manually annotating …...

AbstractLarge pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model’s parameters, …...