DeepAI AI Chat
Log In Sign Up

Debiasing Embeddings for Reduced Gender Bias in Text Classification

by   Flavien Prost, et al.

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation classification (De-Arteaga et al.,2019). We show that traditional techniques for debiasing embeddings can actually worsen the bias of the downstream classifier by providing a less noisy channel for communicating gender information. With a relatively minor adjustment, however, we show how these same techniques can be used to simultaneously reduce bias and maintain high classification accuracy.


page 1

page 2

page 3

page 4


Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation

Bolukbasi et al. (2016) presents one of the first gender bias mitigation...

How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification

To mitigate gender bias in contextualized language models, different int...

Towards classification parity across cohorts

Recently, there has been a lot of interest in ensuring algorithmic fairn...

Controlling Bias Exposure for Fair Interpretable Predictions

Recent work on reducing bias in NLP models usually focuses on protecting...

Grammatical Gender, Neo-Whorfianism, and Word Embeddings: A Data-Driven Approach to Linguistic Relativity

The relation between language and thought has occupied linguists for at ...

Gender bias in (non)-contextual clinical word embeddings for stereotypical medical categories

Clinical word embeddings are extensively used in various Bio-NLP problem...

MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline

Existing methods for debiasing word embeddings often do so only superfic...