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...

Descripció completa

Dades bibliogràfiques
Autors principals: Hofmann, V, Pierrehumbert, J, Schütze, H
Format: Conference item
Idioma:English
Publicat: Journal of Machine Learning Research 2022