Abstract
Using data from English cloze tests, in which subjects also self-reported their gender, age, education, and race, we examine performance differences of pretrained language models across demographic groups, defined by these (protected) attributes. We demonstrate wide performance gaps across demographic groups and show that pretrained language models systematically disfavor young non-white male speakers; i.e., not only do pretrained language models learn social biases (stereotypical associations) – pretrained language models also learn sociolectal biases, learning to speak more like some than like others. We show, however, that, with the exception of BERT models, larger pretrained language models reduce some the performance gaps between majority and minority groups.- Anthology ID:
- 2021.emnlp-main.375
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4581–4588
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.375
- DOI:
- 10.18653/v1/2021.emnlp-main.375
- Cite (ACL):
- Sheng Zhang, Xin Zhang, Weiming Zhang, and Anders Søgaard. 2021. Sociolectal Analysis of Pretrained Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4581–4588, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Sociolectal Analysis of Pretrained Language Models (Zhang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.375.pdf