Mitigating Gender Bias in Neural Machine Translation Using Counterfactual Data

Author

Alan Wong, The Graduate Center, City University of New YorkFollow

Date of Degree

9-2020

Document Type

Thesis

Degree Name

M.A.

Program

Linguistics

Advisor

Kyle Gorman

Subject Categories

Computational Linguistics

Keywords

neural networks, natural language processing

Abstract

Recent advances in deep learning have greatly improved the ability of researchers to develop effective machine translation systems. In particular, the application of modern neural architectures, such as the Transformer, has achieved state-of-the-art BLEU scores in many translation tasks. However, it has been found that even state-of-the-art neural machine translation models can suffer from certain implicit biases, such as gender bias (Lu et al., 2019). In response to this issue, researchers have proposed various potential solutions: some have proposed approaches that inject missing gender information into models, while others have attempted modifying the training data itself. We focus on mitigating gender bias through the use of both counterfactual data augmentation and data substitution techniques, exploring how the two techniques compare when applied to different datasets, how gender bias mitigation varies with the amount of counterfactual data used, and how these techniques may affect BLEU score.

Recommended Citation

Wong, Alan, "Mitigating Gender Bias in Neural Machine Translation Using Counterfactual Data" (2020). CUNY Academic Works.
https://academicworks.cuny.edu/gc_etds/3990