# Using Adversarial Debiasing to Remove Bias from Word Embeddings

arXiv: https://arxiv.org/abs/2107.10251 · HTML: https://mlsanity.com/paper/2107.10251/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 6 references that are in the map.
- First posted on arXiv 21 Jul 2021.

## Builds on (most cited first, 6 of 6)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [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)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [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)
- [Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction](https://mlsanity.com/paper/1807.00199/) (2018)

## Built on by (most cited first, 2 of 2)

- [Developing a novel fair-loan-predictor through a multi-sensitive debiasing pipeline: DualFair](https://mlsanity.com/paper/2110.08944/) (2021)
- [Adversarial Learned Fair Representations using Dampening and Stacking](https://mlsanity.com/paper/2203.08637/) (2022)

## Abstract (arXiv)

Word Embeddings have been shown to contain the societal biases present in the original corpora. Existing methods to deal with this problem have been shown to only remove superficial biases. The method of Adversarial Debiasing was presumed to be similarly superficial, but this is was not verified in previous works. Using the experiments that demonstrated the shallow removal in other methods, I show results that suggest Adversarial Debiasing is more effective at removing bias and thus motivate further investigation on the utility of Adversarial Debiasing.