Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts

TL;DR

This paper demonstrates that few-shot cross-lingual transfer with pre-trained language models significantly improves de-identification of code-mixed clinical texts in low-resource settings, achieving high F1-scores.

Contribution

It empirically shows the effectiveness of few-shot transfer learning for multilingual clinical text de-identification, especially in code-mixed languages.

Findings

F1-score improved from 73.7% to 91.2% with few-shot transfer.

Achieved a human-evaluation F1-score of 97.2% on out-of-sample data.

Demonstrated effectiveness in low-resource, code-mixed clinical text de-identification.

Abstract

Despite the advances in digital healthcare systems offering curated structured knowledge, much of the critical information still lies in large volumes of unlabeled and unstructured clinical texts. These texts, which often contain protected health information (PHI), are exposed to information extraction tools for downstream applications, risking patient identification. Existing works in de-identification rely on using large-scale annotated corpora in English, which often are not suitable in real-world multilingual settings. Pre-trained language models (LM) have shown great potential for cross-lingual transfer in low-resource settings. In this work, we empirically show the few-shot cross-lingual transfer property of LMs for named entity recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke domain. We annotate a gold evaluation dataset to assess few-shot setting performance where we only use a few hundred labeled examples for training. Our model improves the zero-shot F1-score from 73.7% to 91.2% on the gold evaluation set when adapting Multilingual BERT (mBERT) (Devlin et al., 2019) from the MEDDOCAN (Marimon et al., 2019) corpus with our few-shot cross-lingual target corpus. When generalized to an out-of-sample test set, the best model achieves a human-evaluation F1-score of 97.2%.