Self-supervised pre-training on unlabeled clinical notes reduced the labeled data needed for ER trauma classification by roughly 10x, but the estimate is weakened by test-set-based model selection and missing variance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pre-training A Neural Language Model Improves The Sample Efficiency of an Emergency Room Classification Model
Self-supervised pre-training on unlabeled clinical notes reduced the labeled data needed for ER trauma classification by roughly 10x, but the estimate is weakened by test-set-based model selection and missing variance.