# Debiasing Multilingual Word Embeddings: A Case Study of Three Indian Languages

arXiv: https://arxiv.org/abs/2107.10181 · HTML: https://mlsanity.com/paper/2107.10181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 21 Jul 2021.

## Builds on (most cited first, 17 of 17)

- [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)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [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)
- [Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate](https://mlsanity.com/paper/1809.02208/) (2018)
- [On Measuring and Mitigating Biased Inferences of Word Embeddings](https://mlsanity.com/paper/1908.09369/) (2019)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)
- [Attenuating Bias in Word Vectors](https://mlsanity.com/paper/1901.07656/) (2019)
- [Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00699/) (2020)
- [How Language-Neutral is Multilingual BERT?](https://mlsanity.com/paper/1911.03310/) (2019)
- [Examining Gender Bias in Languages with Grammatical Gender](https://mlsanity.com/paper/1909.02224/) (2019)
- [Massively Multilingual Word Embeddings](https://mlsanity.com/paper/1602.01925/) (2016)
- [A Multilingual Parallel Corpora Collection Effort for Indian Languages](https://mlsanity.com/paper/2007.07691/) (2020)
- [Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages](https://mlsanity.com/paper/1909.09265/) (2019)
- [Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing](https://mlsanity.com/paper/1909.01482/) (2019)

## Built on by (most cited first, 8 of 8)

- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [Gender Bias in Masked Language Models for Multiple Languages](https://mlsanity.com/paper/2205.00551/) (2022)
- [On Evaluating and Mitigating Gender Biases in Multilingual Settings](https://mlsanity.com/paper/2307.01503/) (2023)
- [The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases](https://mlsanity.com/paper/2401.10535/) (2024)
- [Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving](https://mlsanity.com/paper/2112.05194/) (2021)
- [Analyzing Gender Representation in Multilingual Models](https://mlsanity.com/paper/2204.09168/) (2022)
- [ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotyping](https://mlsanity.com/paper/2502.02072/) (2025)
- [ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality](https://mlsanity.com/paper/2402.18797/) (2024)

## Abstract (arXiv)

In this paper, we advance the current state-of-the-art method for debiasing monolingual word embeddings so as to generalize well in a multilingual setting. We consider different methods to quantify bias and different debiasing approaches for monolingual as well as multilingual settings. We demonstrate the significance of our bias-mitigation approach on downstream NLP applications. Our proposed methods establish the state-of-the-art performance for debiasing multilingual embeddings for three Indian languages - Hindi, Bengali, and Telugu in addition to English. We believe that our work will open up new opportunities in building unbiased downstream NLP applications that are inherently dependent on the quality of the word embeddings used.