deb2viz: Debiasing gender in word embedding data using subspace visualization

Enoch Opanin Gyamfi; Yunbo Rao; Miao Gou; Yanhua Shao

doi:10.1117/12.2557465

3 January 2020 deb2viz: Debiasing gender in word embedding data using subspace visualization

Enoch Opanin Gyamfi, Yunbo Rao, Miao Gou, Yanhua Shao

Proceedings Volume 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019); 113732F (2020) https://doi.org/10.1117/12.2557465
Event: Eleventh International Conference on Graphics and Image Processing, 2019, Hangzhou, China

Abstract

Word embedding have been used in numerous Natural Language Processing and Machine Learning tasks. However, it is a high-dimensional vector field that propagate stereotypes to software applications. Its current debiasing frameworks do not completely capture its embedded patterns. In this paper, we propose deb2viz, a visual debiasing approach that explores and manipulates the high-dimensional patterns of word embedding field. First, we partition this vector field into interrelated low-dimensional subspaces to equalize and neutralize distances between gender-definitional and gender-neutral words. To further reduce gender bias, we update the distances of appropriate nearest neighbors for gender-neutral words to be arbitrarily close. Experimental results on several benchmark standards show the competitiveness of our proposed method in mitigating bias within pre-trained word2vec embedding model.

Citation Download Citation

Enoch Opanin Gyamfi, Yunbo Rao, Miao Gou, and Yanhua Shao "deb2viz: Debiasing gender in word embedding data using subspace visualization", Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113732F (3 January 2020); https://doi.org/10.1117/12.2557465

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available