2020/06/20 by Yuhao Du, Kenneth Joseph, Du, Yuhao +1
Computer Science · #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Software Engineering Research #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2006.11642
openalex publication_date 2020/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Existing methods for debiasing word embeddings often do so only superficially, in that words that are stereotypically associated with, e.g., a particular gender in the original embedding space can still be clustered together in the debiased space. However, there has yet to be a study that explores why this residual clustering exists, and how it might be addressed. The present work fills this gap. We identify two potential reasons for which residual bias exists and develop a new pipeline, MDR Cluster-Debias, to mitigate this bias. We explore the strengths and weaknesses of our method, finding that it significantly outperforms other existing debiasing approaches on a variety of upstream bias tests but achieves limited improvement on decreasing gender bias in a downstream task. This indicates that word embeddings encode gender bias in still other ways, not necessarily captured by upstream tests.