Detecting emergent intersectional biases: Contextualized word embeddings contain a distribution of human-like biases

W Guo, A Caliskan - Proceedings of the 2021 AAAI/ACM Conference on …, 2021 - dl.acm.org
With the starting point that implicit human biases are reflected in the statistical regularities of
language, it is possible to measure biases in English static word embeddings. State-of-the …

Detecting East Asian prejudice on social media

B Vidgen, A Botelho, D Broniatowski, E Guest… - arXiv preprint arXiv …, 2020 - arxiv.org
The outbreak of COVID-19 has transformed societies across the world as governments
tackle the health, economic and social costs of the pandemic. It has also raised concerns …