English

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

Computation and Language 2021-07-23 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2107.10181,
  title  = {Debiasing Multilingual Word Embeddings: A Case Study of Three Indian Languages},
  author = {Srijan Bansal and Vishal Garimella and Ayush Suhane and Animesh Mukherjee},
  journal= {arXiv preprint arXiv:2107.10181},
  year   = {2021}
}

Comments

This work is accepted as a long paper in the proceedings of ACM HyperText 2021

R2 v1 2026-06-24T04:24:11.722Z