Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis

Michael Lepori


Abstract
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases against Black women. We show that these embeddings represent Black women as simultaneously less feminine than White women, and less Black than Black men. This finding aligns with intersectionality theory, which argues that multiple identity categories (such as race or sex) layer on top of each other in order to create unique modes of discrimination that are not shared by any individual category.
Anthology ID:
2020.coling-main.151
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1720–1728
Language:
URL:
https://aclanthology.org/2020.coling-main.151
DOI:
10.18653/v1/2020.coling-main.151
Bibkey:
Cite (ACL):
Michael Lepori. 2020. Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1720–1728, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis (Lepori, COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.151.pdf
Code
 mlepori1/Unequal_Representations