The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations

By João Sedoc, Lyle Ungar. 2019

21 citations recorded by the source corpus.

Systemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied. Standard debiasing methods require heterogeneous lists of target words to identify the “bias subspace”. We show show that using new contextualized word embeddings in conceptor debiasing allows us to more accurately debias word embeddings by breaking target word lists into more homogeneous subsets and then combining (”Or’ing”) the debiasing conceptors of the different subsets.

Subfields: Artificial Intelligence, Natural Language Processing, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In AI Ethics, Fairness & Society

Citations in the corpus

Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics (2021, background): “…line of research measures bias present in sentence or word representations (Bolukbasi et al., 2016; Caliskan et al., 2017; Kurita et al., 2019; Sedoc and Ungar, 2019; Chaloner and Maldon-ado, 2019; Dev and Phillips, 2019; Gonen and Goldberg, 2019; Hall Maudslay et al., 2019; Liang et al.,…”
Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models (2021, methodology): “This approach was then applied to BERTbased models (Sedoc and Ungar, 2019).”
Perturbation Augmentation for Fairer NLP (2022, background): “However, word list approaches are necessarily limited (Dinan et al., 2020a) and which words are included can really matter (Sedoc and Ungar, 2019).”