# A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

arXiv: https://arxiv.org/abs/1911.10787 · HTML: https://mlsanity.com/paper/1911.10787/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 11 of 11)

- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving](https://mlsanity.com/paper/2112.05194/) (2021)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)
- [Counterfactual Multi-Token Fairness in Text Classification](https://mlsanity.com/paper/2202.03792/) (2022)
- [Does Debiasing Inevitably Degrade the Model Performance](https://mlsanity.com/paper/2211.07350/) (2022)
- [For the Underrepresented in Gender Bias Research: Chinese Name Gender Prediction with Heterogeneous Graph Attention Network](https://mlsanity.com/paper/2302.00419/) (2023)
- [Detecting Natural Language Biases with Prompt-based Learning](https://mlsanity.com/paper/2309.05227/) (2023)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)

## Abstract (arXiv)

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks that rely on these biased word vectors also produce gender-biased results. While some word-embedding gender-debiasing methods have been developed, these methods mainly focus on reducing gender bias associated with gender direction and fail to reduce the gender bias presented in word embedding relations. In this paper, we design a causal and simple approach for mitigating gender bias in word vector relation by utilizing the statistical dependency between gender-definition word embeddings and gender-biased word embeddings. Our method attains state-of-the-art results on gender-debiasing tasks, lexical- and sentence-level evaluation tasks, and downstream coreference resolution tasks.