Socially Aware Bias Measurements for Hindi Language Representations

Vijit Malik, Sunipa Dev, Akihiro Nishi, Nanyun Peng, Kai-Wei Chang


Abstract
Language representations are an efficient tool used across NLP, but they are strife with encoded societal biases. These biases are studied extensively, but with a primary focus on English language representations and biases common in the context of Western society. In this work, we investigate the biases present in Hindi language representations such as caste and religion associated biases. We demonstrate how biases are unique to specific language representations based on the history and culture of the region they are widely spoken in, and also how the same societal bias (such as binary gender associated biases) when investigated across languages is encoded by different words and text spans. With this work, we emphasize on the necessity of social-awareness along with linguistic and grammatical artefacts when modeling language representations, in order to understand the biases encoded.
Anthology ID:
2022.naacl-main.76
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1041–1052
Language:
URL:
https://aclanthology.org/2022.naacl-main.76
DOI:
10.18653/v1/2022.naacl-main.76
Bibkey:
Cite (ACL):
Vijit Malik, Sunipa Dev, Akihiro Nishi, Nanyun Peng, and Kai-Wei Chang. 2022. Socially Aware Bias Measurements for Hindi Language Representations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1041–1052, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Socially Aware Bias Measurements for Hindi Language Representations (Malik et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.76.pdf
Software:
 2022.naacl-main.76.software.zip
Code
 vijit-m/sochindi