Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?

Rochelle Choenni, Ekaterina Shutova, Robert van Rooij


Abstract
In this paper, we investigate what types of stereotypical information are captured by pretrained language models. We present the first dataset comprising stereotypical attributes of a range of social groups and propose a method to elicit stereotypes encoded by pretrained language models in an unsupervised fashion. Moreover, we link the emergent stereotypes to their manifestation as basic emotions as a means to study their emotional effects in a more generalized manner. To demonstrate how our methods can be used to analyze emotion and stereotype shifts due to linguistic experience, we use fine-tuning on news sources as a case study. Our experiments expose how attitudes towards different social groups vary across models and how quickly emotions and stereotypes can shift at the fine-tuning stage.
Anthology ID:
2021.emnlp-main.111
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1477–1491
Language:
URL:
https://aclanthology.org/2021.emnlp-main.111
DOI:
10.18653/v1/2021.emnlp-main.111
Bibkey:
Cite (ACL):
Rochelle Choenni, Ekaterina Shutova, and Robert van Rooij. 2021. Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1477–1491, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you? (Choenni et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.111.pdf