A Multilabel Approach to Portuguese Clinical Named Entity Recognition
Palavras-chave:
Clinical Named Entity Recognition, Label Powerset, BERTResumo
Objectives: Clinical Named Entity Recognition is a critical Natural Language Processing task, as it could support biomedical research and healthcare systems. While most extracted clinical entities are based on single-label concepts, it is very common in the clinical domain entities with more than one semantic category simultaneously. This work proposes BERT-based models to support multilabel clinical named entity recognition in the Portuguese language. Methods: For the experiment, we used the Label Powerset method applied to the multilabel corpus SemClinBr. Results: We compare our results with a Conditional Random Fields baseline, reaching +2.1 in precision, +11.2 in recall, and +7.4 in F1 with a clinical-biomedical BERT model (BioBERTpt). Conclusion: We achieved higher results for both exact and partial metrics, contributing to the multilabel semantic processing of clinical narratives in Portuguese.Downloads
Não há dados estatísticos.
Downloads
Publicado
15-03-2021
Como Citar
Souza, J. V. A. de, Schneider, E. T. R., Cezar, J. O., Oliveira, L. E. S. e, Gumiel, Y. B., Paraiso, E. C., … Barra, C. M. C. M. (2021). A Multilabel Approach to Portuguese Clinical Named Entity Recognition. Journal of Health Informatics, 12. Recuperado de https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/840
Edição
Seção
Artigo Original
Licença
Vale a licença indicada em cada artigo, na sua página e no PDF. A partir do volume 18 (2026), o Journal of Health Informatics adota a licença Creative Commons Atribuição 4.0 Internacional (CC BY 4.0), que permite copiar, distribuir, adaptar e reutilizar o conteúdo para qualquer fim, desde que a autoria e a fonte original sejam citadas. Artigos publicados até 2025 permanecem sob a licença Creative Commons Atribuição–Não Comercial–Compartilha Igual 4.0 Internacional (CC BY-NC-SA 4.0).
