Kris Cao, Laura Rimell. You should evaluate your language model on marginal likelihood over tokenisations. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021. pages 2104-2114, Association for Computational Linguistics, 2021. [doi]
Abstract is missing.