@article{mantaefficientgradientbasedtokenization, title = {MANTa: Efficient Gradient-Based Tokenization for Robust End-to-End Language Modeling}, author = {Nathan Godey and Roman Castagné and Éric de la Clergerie and Benoît Sagot}, year = {2022}, eprint = {2212.07284}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2212.07284v1}, }