Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens Itay Itzhak author Omer Levy author 2022-07 text Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Marine Carpuat editor Marie-Catherine de Marneffe editor Ivan Vladimir Meza Ruiz editor Association for Computational Linguistics Seattle, United States conference publication itzhak-levy-2022-models 10.18653/v1/2022.naacl-main.373 https://aclanthology.org/2022.naacl-main.373/ 2022-07 5061 5068