Measuring Gender Bias in West Slavic Language Models

Sandra Martinková, Karolina Stanczak, Isabelle Augenstein


Abstract
Pre-trained language models have been known to perpetuate biases from the underlying datasets to downstream tasks. However, these findings are predominantly based on monolingual language models for English, whereas there are few investigative studies of biases encoded in language models for languages beyond English. In this paper, we fill this gap by analysing gender bias in West Slavic language models. We introduce the first template-based dataset in Czech, Polish, and Slovak for measuring gender bias towards male, female and non-binary subjects. We complete the sentences using both mono- and multilingual language models and assess their suitability for the masked language modelling objective. Next, we measure gender bias encoded in West Slavic language models by quantifying the toxicity and genderness of the generated words. We find that these language models produce hurtful completions that depend on the subject’s gender. Perhaps surprisingly, Czech, Slovak, and Polish language models produce more hurtful completions with men as subjects, which, upon inspection, we find is due to completions being related to violence, death, and sickness.
Anthology ID:
2023.bsnlp-1.17
Original:
2023.bsnlp-1.17v1
Version 2:
2023.bsnlp-1.17v2
Volume:
Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Jakub Piskorski, Michał Marcińczuk, Preslav Nakov, Maciej Ogrodniczuk, Senja Pollak, Pavel Přibáň, Piotr Rybak, Josef Steinberger, Roman Yangarber
Venue:
BSNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
146–154
Language:
URL:
https://aclanthology.org/2023.bsnlp-1.17
DOI:
10.18653/v1/2023.bsnlp-1.17
Bibkey:
Cite (ACL):
Sandra Martinková, Karolina Stanczak, and Isabelle Augenstein. 2023. Measuring Gender Bias in West Slavic Language Models. In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pages 146–154, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Measuring Gender Bias in West Slavic Language Models (Martinková et al., BSNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.bsnlp-1.17.pdf
Video:
 https://aclanthology.org/2023.bsnlp-1.17.mp4