Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology
Valentin Hofmann, Janet Pierrehumbert, Hinrich Schütze
Abstract
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 capturing this information. As a concrete example, we focus on the phenomenon of ideological bias: we introduce the concept of an ideological subspace, show how it can be found by applying our method to online discussion forums, and present techniques to probe it. Our experiments suggest that the ideological subspace encodes abstract evaluative semantics and reflects changes in the political left-right spectrum during the presidency of Donald Trump.
BibTeX
@InProceedings{pmlr-v162-hofmann22a,
title = {Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology},
author = {Hofmann, Valentin and Pierrehumbert, Janet and Sch{\"u}tze, Hinrich},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {8796--8810},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/hofmann22a/hofmann22a.pdf},
url = {https://proceedings.mlr.press/v162/hofmann22a.html},
abstract = {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 capturing this information. As a concrete example, we focus on the phenomenon of ideological bias: we introduce the concept of an ideological subspace, show how it can be found by applying our method to online discussion forums, and present techniques to probe it. Our experiments suggest that the ideological subspace encodes abstract evaluative semantics and reflects changes in the political left-right spectrum during the presidency of Donald Trump.}
}