@article{exploringtheimpactoftrainingdata, title = {Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation}, author = {Bar Iluz and Tomasz Limisiewicz and Gabriel Stanovsky and David Mareček}, year = {2023}, eprint = {2309.12491}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2309.12491v2}, }