Метод Устранения Уклонов

AbstractWord embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that …...

AbstractWord embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words …...

AbstractDebiasing language models from unwanted behaviors in Natural Language Understanding (NLU) tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow …...

AbstractNatural Language Processing (NLP) models are found to exhibit discriminatory stereotypes across many social constructs, e.g. gender and race. In comparison to the progress made in reducing bias from static …...

AbstractRecent breakthroughs in self-supervised training have led to a new class of pretrained vision–language models. While there have been investigations of bias in multimodal models, they have mostly focused on …...