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...
المؤلفون الرئيسيون: | Hofmann, V, Pierrehumbert, J, Schütze, H |
---|---|
التنسيق: | Conference item |
اللغة: | English |
منشور في: |
Journal of Machine Learning Research
2022
|
مواد مشابهة
-
Dynamic contextualized word embeddings
حسب: Hofmann, V, وآخرون
منشور في: (2021) -
Leveraging Bias in Pre-trained Word Embeddings for Unsupervised Microaggression Detection
حسب: Tolúlọpẹ́ Ògúnrẹ̀mí, وآخرون
منشور في: (2022-12-01) -
Unsupervised Bitext Mining and Translation via Self-Trained Contextual Embeddings
حسب: Phillip Keung, وآخرون
منشور في: (2021-03-01) -
Forecasting COVID-19 caseloads using unsupervised embedding clusters of social media posts
حسب: Drinkall, F, وآخرون
منشور في: (2022) -
Modeling ideological salience and framing in polarized online groups with graph neural networks and structured sparsity
حسب: Hofmann, V, وآخرون
منشور في: (2022)