Unsupervised detection of contextualized embedding bias with application to ideology

We propose a fully unsupervised method to detect bias in contextualized embeddings. The method leverages the assortative information latently encoded by social networks and combines orthogonality regularization, structured sparsity learning, and graph neural networks to find the embedding subspace c...

ver descrição completa

Detalhes bibliográficos
Principais autores: Hofmann, V, Pierrehumbert, J, Schütze, H
Formato: Conference item
Idioma:English
Publicado em: Journal of Machine Learning Research 2022