Advanced search
1 file | 467.42 KB Add to list

GENDEROUS : machine translation and cross-linguistic evaluation of a gender-ambiguous dataset

Janica Hackenbuchner (UGent) , Eleni Gkovedarou (UGent) and Joke Daems (UGent)
Author
Organization
Project
Abstract
Contributing to research on gender beyond the binary, this work introduces GENDEROUS, a dataset of gender-ambiguous sentences containing gender-marked occupations and adjectives, and sentences with the ambiguous or non-binary pronoun their. We cross-linguistically evaluate how machine translation (MT) systems and large language models (LLMs) translate these sentences from English into four grammatical gender languages: Greek, German, Spanish and Dutch. We show the systems’ continued default to male-gendered translations, with exceptions (particularly for Dutch). Prompting for alternatives, however, shows potential in attaining more diverse and neutral translations across all languages. An LLM-as-a-judge approach was implemented, where benchmarking against gold standards emphasises the continued need for human annotations.

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 467.42 KB

Citation

Please use this url to cite or link to this publication:

MLA
Hackenbuchner, Janica, et al. “GENDEROUS : Machine Translation and Cross-Linguistic Evaluation of a Gender-Ambiguous Dataset.” NITS Conference 2025, Abstracts, 2025.
APA
Hackenbuchner, J., Gkovedarou, E., & Daems, J. (2025). GENDEROUS : machine translation and cross-linguistic evaluation of a gender-ambiguous dataset. NITS Conference 2025, Abstracts. Presented at the Network of Interdisciplinary Translation Studies in the Netherlands and Flanders (NITS), Tilburg, The Netherlands.
Chicago author-date
Hackenbuchner, Janica, Eleni Gkovedarou, and Joke Daems. 2025. “GENDEROUS : Machine Translation and Cross-Linguistic Evaluation of a Gender-Ambiguous Dataset.” In NITS Conference 2025, Abstracts.
Chicago author-date (all authors)
Hackenbuchner, Janica, Eleni Gkovedarou, and Joke Daems. 2025. “GENDEROUS : Machine Translation and Cross-Linguistic Evaluation of a Gender-Ambiguous Dataset.” In NITS Conference 2025, Abstracts.
Vancouver
1.
Hackenbuchner J, Gkovedarou E, Daems J. GENDEROUS : machine translation and cross-linguistic evaluation of a gender-ambiguous dataset. In: NITS conference 2025, Abstracts. 2025.
IEEE
[1]
J. Hackenbuchner, E. Gkovedarou, and J. Daems, “GENDEROUS : machine translation and cross-linguistic evaluation of a gender-ambiguous dataset,” in NITS conference 2025, Abstracts, Tilburg, The Netherlands, 2025.
@inproceedings{01K94X05N04FBZC4FJN21T6FBT,
  abstract     = {{Contributing to research on gender beyond the binary, this work introduces GENDEROUS, a dataset of gender-ambiguous sentences containing gender-marked occupations and adjectives, and sentences with the ambiguous or non-binary pronoun their. We cross-linguistically evaluate how machine translation (MT) systems and large language models (LLMs) translate these sentences from English into four grammatical gender languages: Greek, German, Spanish and Dutch. We show the systems’ continued default to male-gendered translations, with exceptions (particularly for Dutch). Prompting for alternatives, however, shows potential in attaining more diverse and neutral translations across all languages. An LLM-as-a-judge approach was implemented, where benchmarking against gold standards emphasises the continued need for human annotations.}},
  author       = {{Hackenbuchner, Janica and Gkovedarou, Eleni and Daems, Joke}},
  booktitle    = {{NITS conference 2025, Abstracts}},
  language     = {{eng}},
  location     = {{Tilburg, The Netherlands}},
  title        = {{GENDEROUS : machine translation and cross-linguistic evaluation of a gender-ambiguous dataset}},
  url          = {{https://nitsnetwork.github.io/programme.html}},
  year         = {{2025}},
}