Skip to Main content Skip to Navigation
Journal articles

Word embedding for French natural language in healthcare: a comparative study (Preprint)

Emeric Dynomant 1, 2 Romain Lelong 3, 2 Badisse Dahamna 3, 4 Clément Massonnaud 3 Gaétan Kerdelhué 3, 4 Julien Grosjean 3, 4 Stephane Canu 5 Stefan Darmoni 4, 3
1 OmicX
2 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
3 Service d'informatique biomédicale [Rouen]
4 LIMICS - Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé
5 DocApp - LITIS - Equipe Apprentissage
LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
Abstract : Word embedding technologies, a set of language modeling and feature learning techniques in natural language processing (NLP), are now used in a wide range of applications. However, no formal evaluation and comparison have been made on the ability of each of the 3 current most famous unsupervised implementations (Word2Vec, GloVe, and FastText) to keep track of the semantic similarities existing between words, when trained on the same dataset.
Keywords : natural language processing data curation data mining
Document type :
Journal articles
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download
https://hal.sorbonne-universite.fr/hal-02321827
Contributor : Hal Sorbonne Université Gestionnaire <>
Submitted on : Monday, October 21, 2019 - 3:13:20 PM
Last modification on : Thursday, December 10, 2020 - 12:33:54 PM
Long-term archiving on: : Wednesday, January 22, 2020 - 3:58:34 PM

File

Vignette du document
document.pdf
Publisher files allowed on an open archive

Identifiers

Collections

LITIS | INSA-ROUEN | UNIROUEN | UNILEHAVRE | INSA-GROUPE | COMUE-NORMANDIE | LIMICS | UNIV-PARIS13 | SORBONNE-UNIVERSITE | SU-SCIENCES | USPC | SU-TI

Citation

Emeric Dynomant, Romain Lelong, Badisse Dahamna, Clément Massonnaud, Gaétan Kerdelhué, et al.. Word embedding for French natural language in healthcare: a comparative study (Preprint). JMIR Medical Informatics, JMIR Publications, 2019, ⟨10.2196/12310⟩. ⟨hal-02321827⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

321

Files downloads

232