Word embedding for French natural language in healthcare: a comparative study (Preprint) - Archive ouverte HAL Access content directly
Journal Articles JMIR Medical Informatics Year : 2019

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

(1, 2) , (3, 2) , (3) , (3) , (3, 4) , (3, 4) , (2) , (4, 3)
1
2
3
4

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.
Fichier principal
Vignette du fichier
document.pdf (628.24 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-02321827 , version 1 (21-10-2019)

Identifiers

Cite

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, 2019, ⟨10.2196/12310⟩. ⟨hal-02321827⟩
661 View
271 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More