# Debiasing Word Embeddings with Nonlinear Geometry

arXiv: https://arxiv.org/abs/2208.13899 · HTML: https://mlsanity.com/paper/2208.13899/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Assessing Social and Intersectional Biases in Contextualized Word Representations](https://mlsanity.com/paper/1911.01485/) (2019)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models](https://mlsanity.com/paper/2112.07447/) (2021)
- [Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis](https://mlsanity.com/paper/2011.12086/) (2020)
- [Native Language Cognate Effects on Second Language Lexical Choice](https://mlsanity.com/paper/1805.09590/) (2018)
- [Autoencoding Improves Pre-trained Word Embeddings](https://mlsanity.com/paper/2010.13094/) (2020)
- [Toward Understanding Bias Correlations for Mitigation in NLP](https://mlsanity.com/paper/2205.12391/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges](https://mlsanity.com/paper/2305.06969/) (2023)
- [Fairness through Aleatoric Uncertainty](https://mlsanity.com/paper/2304.03646/) (2023)
- [Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts](https://mlsanity.com/paper/2310.10865/) (2023)

## Abstract (arXiv)

Debiasing word embeddings has been largely limited to individual and independent social categories. However, real-world corpora typically present multiple social categories that possibly correlate or intersect with each other. For instance, "hair weaves" is stereotypically associated with African American females, but neither African American nor females alone. Therefore, this work studies biases associated with multiple social categories: joint biases induced by the union of different categories and intersectional biases that do not overlap with the biases of the constituent categories. We first empirically observe that individual biases intersect non-trivially (i.e., over a one-dimensional subspace). Drawing from the intersectional theory in social science and the linguistic theory, we then construct an intersectional subspace to debias for multiple social categories using the nonlinear geometry of individual biases. Empirical evaluations corroborate the efficacy of our approach. Data and implementation code can be downloaded at https://github.com/GitHubLuCheng/Implementation-of-JoSEC-COLING-22.