mlsanityData to 14 Oct 2026

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

arXiv 2107.10181 ↗First posted 21 Jul 2021cs.CLcited by 8

Not on the map. Why?

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.

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

17 of 21 references.

References · 17

  1. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  2. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  3. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  4. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 455
  5. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  6. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  7. 2018Assessing Gender Bias in Machine Translation -- A Case Study with Google Translatecited by 121
  8. 2019On Measuring and Mitigating Biased Inferences of Word Embeddingscited by 112
  9. 2017Offline bilingual word vectors, orthogonal transformations and the inverted softmaxcited by 96
  10. 2019Attenuating Bias in Word Vectorscited by 64
  11. 2020Gender Bias in Multilingual Embeddings and Cross-Lingual Transfercited by 55
  12. 2019How Language-Neutral is Multilingual BERT?cited by 51
5 more
  1. 2019Examining Gender Bias in Languages with Grammatical Gendercited by 40
  2. 2016Massively Multilingual Word Embeddingscited by 26
  3. 2020A Multilingual Parallel Corpora Collection Effort for Indian Languagescited by 16
  4. 2019Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languagescited by 13
  5. 2019Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsingcited by 11

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 3; 2025: 1.

8 papers.

  1. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
  2. 2022Gender Bias in Masked Language Models for Multiple Languagescited by 60
  3. 2023On Evaluating and Mitigating Gender Biases in Multilingual Settingscited by 31
  4. 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
  5. 2021Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preservingcited by 11
  6. 2022Analyzing Gender Representation in Multilingual Modelscited by 10
  7. 2025ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotypingcited by 1
  8. 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Realitycited by 0