Tianshuai Lu


2023

pdf
Reducing Gender Bias in NMT with FUDGE
Tianshuai Lu | Noëmi Aepli | Annette Rios
Proceedings of the First Workshop on Gender-Inclusive Translation Technologies

Gender bias appears in many neural machine translation (NMT) models and commercial translation software. Research has become more aware of this problem in recent years and there has been work on mitigating gender bias. However, the challenge of addressing gender bias in NMT persists. This work utilizes a controlled text generation method, Future Discriminators for Generation (FUDGE), to reduce the so-called Speaking As gender bias. This bias emerges when translating from English to a language that openly marks the gender of the speaker. We evaluate the model on MuST-SHE, a challenge set to specifically evaluate gender translation. The results demonstrate improvements in the translation accuracy of the feminine terms.