Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender

Ahmed Sabir, Lluís Padró


Abstract
In this paper, we investigate the impact of objects on gender bias in image captioning systems. Our results show that only gender-specific objects have a strong gender bias (e.g., women-lipstick). In addition, we propose a visual semantic-based gender score that measures the degree of bias and can be used as a plug-in for any image captioning system. Our experiments demonstrate the utility of the gender score, since we observe that our score can measure the bias relation between a caption and its related gender; therefore, our score can be used as an additional metric to the existing Object Gender Co-Occ approach.
Anthology ID:
2023.findings-emnlp.279
Original:
2023.findings-emnlp.279v1
Version 2:
2023.findings-emnlp.279v2
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4234–4240
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.279
DOI:
Bibkey:
Cite (ACL):
Ahmed Sabir and Lluís Padró. 2023. Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4234–4240, Singapore. Association for Computational Linguistics.
Cite (Informal):
Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender (Sabir & Padró, Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-emnlp.279.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-emnlp.279.mp4