@inproceedings{howrobustisneuralmachinetranslationto, title = {How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?}, author = {Shiyue Zhang and Vishrav Chaudhary and Naman Goyal and James Cross and Guillaume Wenzek and Mohit Bansal and Francisco Guzman}, year = {2022}, booktitle = {AMTA 2022 9}, eprint = {2204.14268}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2204.14268v2}, }