Handling Name Errors of a BERT-Based De-Identification System: Insights from Stratified Sampling and Markov-based Pseudonymization

Handling Name Errors of a BERT-Based De-Identification System: Insights from Stratified Sampling and Markov-based Pseudonymization Dalton Simancek author V.G.Vinod Vydiswaran author 2024-03 text Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024) Elena Volodina editor David Alfter editor Simon Dobnik editor Therese Lindström Tiedemann editor Ricardo Muñoz Sánchez editor Maria Irena Szawerna editor Xuan-Son Vu editor Association for Computational Linguistics St. Julian’s, Malta conference publication simancek-vydiswaran-2024-handling 10.18653/v1/2024.caldpseudo-1.1 https://aclanthology.org/2024.caldpseudo-1.1/ 2024-03 1 7