Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910625784922112 |
|---|---|
| author | Pikuliak, Matúš Hrckova, Andrea Oresko, Stefan Šimko, Marián |
| author_facet | Pikuliak, Matúš Hrckova, Andrea Oresko, Stefan Šimko, Marián |
| contents | We present GEST -- a new manually created dataset designed to measure gender-stereotypical reasoning in language models and machine translation systems. GEST contains samples for 16 gender stereotypes about men and women (e.g., Women are beautiful, Men are leaders) that are compatible with the English language and 9 Slavic languages. The definition of said stereotypes was informed by gender experts. We used GEST to evaluate English and Slavic masked LMs, English generative LMs, and machine translation systems. We discovered significant and consistent amounts of gender-stereotypical reasoning in almost all the evaluated models and languages. Our experiments confirm the previously postulated hypothesis that the larger the model, the more stereotypical it usually is. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_18711 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling Pikuliak, Matúš Hrckova, Andrea Oresko, Stefan Šimko, Marián Computation and Language We present GEST -- a new manually created dataset designed to measure gender-stereotypical reasoning in language models and machine translation systems. GEST contains samples for 16 gender stereotypes about men and women (e.g., Women are beautiful, Men are leaders) that are compatible with the English language and 9 Slavic languages. The definition of said stereotypes was informed by gender experts. We used GEST to evaluate English and Slavic masked LMs, English generative LMs, and machine translation systems. We discovered significant and consistent amounts of gender-stereotypical reasoning in almost all the evaluated models and languages. Our experiments confirm the previously postulated hypothesis that the larger the model, the more stereotypical it usually is. |
| title | Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.18711 |