@inproceedings{schmidt-etal-2024-tokenization, title = "Tokenization Is More Than Compression", author = "Schmidt, Craig W and Reddy, Varshini and Zhang, Haoran and Alameddine, Alec and Uzan, Omri and Pinter, Yuval and Tanner, Chris", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.40/", doi = "10.18653/v1/2024.emnlp-main.40", pages = "678--702" }