Examining Covert Gender Bias: A Case Study in Turkish and English Machine Translation Models
This work addresses bias in machine translation for users and developers, but it is incremental as it builds on existing research on overt bias.
The study tackled the problem of covert gender bias in machine translation models by analyzing Turkish and English, revealing asymmetrical gender markings and stereotypes in occupational and personality attributions, demonstrating the need for language-specific approaches.
As Machine Translation (MT) has become increasingly more powerful, accessible, and widespread, the potential for the perpetuation of bias has grown alongside its advances. While overt indicators of bias have been studied in machine translation, we argue that covert biases expose a problem that is further entrenched. Through the use of the gender-neutral language Turkish and the gendered language English, we examine cases of both overt and covert gender bias in MT models. Specifically, we introduce a method to investigate asymmetrical gender markings. We also assess bias in the attribution of personhood and examine occupational and personality stereotypes through overt bias indicators in MT models. Our work explores a deeper layer of bias in MT models and demonstrates the continued need for language-specific, interdisciplinary methodology in MT model development.