Assessing the Impact of Gender Stereotypes on Machine Translation of Dialogue
Gender stereotypes significantly impact the accuracy of machine translation systems, particularly in resolving the gender of speakers in dialogue, even when unambiguous gender information is provided in the source text.
A Review of Gender Bias Detection and Mitigation in Machine Translation: Focusing on European and African Languages
Research on gender bias in machine translation heavily favors a few high-resource European languages, neglecting many African and even some European languages, highlighting a need for more diverse and inclusive research in the field.
MiTTenS: A Dataset for Evaluating Gender Mistranslation, Covering 26 Languages and Highlighting Systemic Issues in Translation Systems
This paper introduces MiTTenS, a novel dataset designed to evaluate and mitigate gender mistranslation in both dedicated translation systems and large language models, revealing systemic biases and paving the way for fairer and more inclusive language technologies.
Quantifying the Tangible Impact of Gender Bias in Machine Translation on User Experience and Economic Costs
Gender bias in machine translation leads to significant disparities in the time and technical effort required for users to post-edit translations, resulting in higher economic costs that can unfairly fall on different stakeholders.
Gender Bias Evaluation in Machine Translation Systems
Gender bias persists in commercial machine translation systems, impacting the accuracy of gender translations.
© 2024 by Linnk AI