WinoTR: Evaluating Gender Bias in Machine Translation from a Gender-Neutral Language Using Causal Inference

Deniz Albayrak


Abstract
We present WinoTR, a Turkish adaptation of the WinoMT challenge dataset (Stanovsky et al., 2019). While WinoMT has been widely studied across multiple languages, its adaptation to Turkish — a morphologically rich language with no grammatical gender — and its analysis through a causal lens remain unexplored. Using 4,752 sentences adapted from the original dataset across pro-stereotypical, anti-stereotypical, and neutral conditions, we apply Double Machine Learning (DML) to estimate the causal effect of gender cues on stereotype-consistent translation output. Our results reveal a striking asymmetry: cue direction has a large and statistically significant effect on translation outcomes, while cue presence alone produces virtually no effect. Even without any gender signal, MT systems default to stereotype-consistent translations in 62.9% of cases across three systems (DeepL, Google Translate, OpenAI). By leveraging this typological property, our causal analysis reveals that gender bias in contemporary MT and LLM-based translation systems runs deeper than surface-level cue processing, persisting as an embedded prior independent of any explicit gender signal in the input.
Anthology ID:
2026.gitt-1.9
Volume:
Proceedings of the 4th Workshop on Gender-Inclusive Translation Technologies (GITT 2026)
Month:
June
Year:
2026
Address:
Tilburg, the Netherlands
Editors:
Manuel Lardelli, Beatrice Savoldi, Janiça Hackenbuchner, Luisa Bentivogli, Eleni Gkovedarou, Joke Daems
Venues:
GITT | WS
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
100–107
Language:
URL:
https://aclanthology.org/2026.gitt-1.9/
DOI:
Bibkey:
Cite (ACL):
Deniz Albayrak. 2026. WinoTR: Evaluating Gender Bias in Machine Translation from a Gender-Neutral Language Using Causal Inference. In Proceedings of the 4th Workshop on Gender-Inclusive Translation Technologies (GITT 2026), pages 100–107, Tilburg, the Netherlands. European Association for Machine Translation.
Cite (Informal):
WinoTR: Evaluating Gender Bias in Machine Translation from a Gender-Neutral Language Using Causal Inference (Albayrak, GITT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.gitt-1.9.pdf