Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation

Samhita Honnavalli, Aesha Parekh, Lily Ou, Sophie Groenwold, Sharon Levy, Vicente Ordonez, William Yang Wang


Abstract
Women are often perceived as junior to their male counterparts, even within the same job titles. While there has been significant progress in the evaluation of gender bias in natural language processing (NLP), existing studies seldom investigate how biases toward gender groups change when compounded with other societal biases. In this work, we investigate how seniority impacts the degree of gender bias exhibited in pretrained neural generation models by introducing a novel framework for probing compound bias. We contribute a benchmark robustness-testing dataset spanning two domains, U.S. senatorship and professorship, created using a distant-supervision method. Our dataset includes human-written text with underlying ground truth and paired counterfactuals. We then examine GPT-2 perplexity and the frequency of gendered language in generated text. Our results show that GPT-2 amplifies bias by considering women as junior and men as senior more often than the ground truth in both domains. These results suggest that NLP applications built using GPT-2 may harm women in professional capacities.
Anthology ID:
2022.lrec-1.177
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
1665–1670
Language:
URL:
https://aclanthology.org/2022.lrec-1.177
DOI:
Bibkey:
Cite (ACL):
Samhita Honnavalli, Aesha Parekh, Lily Ou, Sophie Groenwold, Sharon Levy, Vicente Ordonez, and William Yang Wang. 2022. Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1665–1670, Marseille, France. European Language Resources Association.
Cite (Informal):
Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation (Honnavalli et al., LREC 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2022.lrec-1.177.pdf
Code
 aeshapar/gender-seniority-compound-bias-dataset