Medical concept normalization in French using multilingual terminologies and contextual embeddings - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Biomedical Informatics Année : 2021

Medical concept normalization in French using multilingual terminologies and contextual embeddings

Résumé

Introduction: Concept normalization is the task of linking terms from textual medical documents to their concept in terminologies such as the UMLS®. Traditional approaches to this problem depend heavily on the coverage of available resources, which poses a problem for languages other than English. Objective: We present a system for concept normalization in French. We consider textual mentions already extracted and labeled by a named entity recognition system, and we classify these mentions with a UMLS concept unique identifier. We take advantage of the multilingual nature of available terminologies and embedding models to improve concept normalization in French without translation nor direct supervision. Materials and methods: We consider the task as a highly-multiclass classification problem. The terms are encoded with contextualized embeddings and classified via cosine similarity and softmax. A first step uses a subset of the terminology to finetune the embeddings and train the model. A second step adds the entire target terminology, and the model is trained further with hard negative selection and softmax sampling. Results: On two corpora from the Quaero FrenchMed benchmark, we show that our approach can lead to good results even with no labeled data at all; and that it outperforms existing supervised methods with labeled data. Discussion: Training the system with both French and English terms improves by a large margin the performance of the system on a French benchmark, regardless of the way the embeddings were pretrained (French, English, multilingual). Our distantly supervised method can be applied to any kind of documents or medical domain, as it does not require any concept-labeled documents. Conclusion: These experiments pave the way for simpler and more effective multilingual approaches to processing medical texts in languages other than English.
Fichier principal
Vignette du fichier
S1532046421000137.pdf (1.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03127411 , version 1 (13-02-2023)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Perceval Wajsbürt, Arnaud Sarfati, Xavier Tannier. Medical concept normalization in French using multilingual terminologies and contextual embeddings. Journal of Biomedical Informatics, 2021, 114, pp.103684. ⟨10.1016/j.jbi.2021.103684⟩. ⟨hal-03127411⟩
135 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More