Evaluation of Word Embeddings from Large-Scale French Web Content - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Evaluation of Word Embeddings from Large-Scale French Web Content

Résumé

Distributed word representations are popularly used in many tasks in natural language processing. Adding that pre-trained word vectors on huge text corpus achieved high performance in many different NLP tasks. This paper introduces multiple high-quality word vectors for the French language where two of them are trained on massive crawled French data during this study and the others are trained on an already existing French corpus. We also evaluate the quality of our proposed word vectors and the existing French word vectors on the French word analogy task. In addition, we do the evaluation on multiple real NLP tasks that shows the important performance enhancement of the pre-trained word vectors compared to the existing and random ones. Finally, we created a demo web application to test and visualize the obtained word embeddings. The produced French word embeddings are available to the public, along with the fine-tuning code on the NLU tasks 2 and the demo code .
Fichier principal
Vignette du fichier
2105.01990.pdf (229.01 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04454559 , version 1 (13-02-2024)

Identifiants

Citer

Hadi Abdine, Christos Xypolopoulos, Moussa Kamal Eddine, Michalis Vazirgiannis. Evaluation of Word Embeddings from Large-Scale French Web Content. Conférence Nationale en Intelligence Artificielle 2022 (CNIA 2022), Jun 2022, Saint-etienne, France. ⟨hal-04454559⟩
4 Consultations
8 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More