Word Embedding for French Natural Language in Healthcare: A Comparative Study. - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Word Embedding for French Natural Language in Healthcare: A Comparative Study.

Résumé

Structuring raw medical documents with ontology mapping is now the next step for medical intelligence. Deep learning models take as input mathematically embedded information, such as encoded texts. To do so, word embedding methods can represent every word from a text as a fixed-length vector. A formal evaluation of three word embedding methods has been performed on raw medical documents. The data corresponds to more than 12M diverse documents produced in the Rouen hospital (drug prescriptions, discharge and surgery summaries, inter-services letters, etc.). Automatic and manual validation demonstrates that Word2Vec based on the skip-gram architecture had the best rate on three out of four accuracy tests. This model will now be used as the first layer of an AI-based semantic annotator.
Fichier non déposé

Dates et versions

hal-02409087 , version 1 (13-12-2019)

Identifiants

Citer

Emeric Dynomant, Romain Lelong, Badisse Dahamna, Clément Massonnaud, Gaetan Kerdelhué, et al.. Word Embedding for French Natural Language in Healthcare: A Comparative Study.. MEDINFO 2019: Health and Wellbeing e-Networks for All, Aug 2019, lyon, France. pp.118-122, ⟨10.3233/SHTI190195⟩. ⟨hal-02409087⟩
200 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More