Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting
| Autor: | Richter-Pechanski, Phillip, Wiesenbach, Philipp, Schwab, Dominic M., Kiriakou, Christina, Geis, Nicolas, Dieterich, Christoph, Frank, Anette |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Automatic extraction of medical information from clinical documents poses several challenges: high costs of required clinical expertise, limited interpretability of model predictions, restricted computational resources and privacy regulations. Recent advances in domain-adaptation and prompting methods showed promising results with minimal training data using lightweight masked language models, which are suited for well-established interpretability methods. We are first to present a systematic evaluation of these methods in a low-resource setting, by performing multi-class section classification on German doctor's letters. We conduct extensive class-wise evaluations supported by Shapley values, to validate the quality of our small training data set and to ensure the interpretability of model predictions. We demonstrate that a lightweight, domain-adapted pretrained model, prompted with just 20 shots, outperforms a traditional classification model by 30.5% accuracy. Our results serve as a process-oriented guideline for clinical information extraction projects working with low-resource. Comment: Paper accepted for publication in the journal: Natural Language Engineering (Cambridge Core) |
| Databáze: | arXiv |
| Externí odkaz: |
|