 |
Journal articles
Word embedding for French natural language in healthcare: a comparative study (Preprint)
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.
Cited literature [38 references]
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 : Saturday, February 15, 2020 - 1:44:44 AM
Document(s) archivé(s) le : Wednesday, January 22, 2020 - 3:58:34 PM
Contributor : Hal Sorbonne Université Gestionnaire <>
Submitted on : Monday, October 21, 2019 - 3:13:20 PM
Last modification on : Saturday, February 15, 2020 - 1:44:44 AM
Document(s) archivé(s) le : Wednesday, January 22, 2020 - 3:58:34 PM
File
document.pdf
Publisher files allowed on an open archive
