Continued pretraining on masked and pseudo-replaced MIMIC-III notes yields strong de-identification models, with masked RoBERTa large performing best and pseudo data helping XLM-RoBERTa more than RoBERTa.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Clinical Models with Pseudo Data for De-identification
Continued pretraining on masked and pseudo-replaced MIMIC-III notes yields strong de-identification models, with masked RoBERTa large performing best and pseudo data helping XLM-RoBERTa more than RoBERTa.