University Sétif 1 FERHAT ABBAS Faculty of Sciences
Détail de l'auteur
Auteur Mafaza, Chabane |
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Affiner la recherche
Titre : Text Classification & Translation Using Transfer Learning and Transformers Type de document : texte imprimé Auteurs : Mafaza, Chabane, Auteur ; Abdelouahab Moussaoui, Directeur de thèse Editeur : Setif:UFA Année de publication : 2021 Importance : 1 vol (91 f .) Format : 29 cm Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Natural language processing
Deep learning
Text classificationIndex. décimale : 004 - Informatique Résumé :
Natural language processing is field of study that focus on building machine learning models
that can read, understand and even generate human language efficiently.
Recently, There have been huge advance and progress in the field of Natural language processing
NLP to bring efficient language models that can understand and process the huge amount of
generated textual data. The Attention mechanism and the Transformer model play a role model,
where recent studies revealed that they achieved higher performance in all NLP tasks.
This work presents a detailed study on recent advances in the field of deep learning applied
to Natural language processing, mainly in Text classification and Neural machine Translation
tasks.
In this work, 10 models in total were replicated and developed then trained and validated on
2 datasets for both Single and Multi label classification, and 2 Machine translation datasets (
Arabic-English and French-English). The experiments show that Transformer based models tend
to give better performance for both Text classification and Machine translation tasks.Côte titre : MAI/0551 En ligne : https://drive.google.com/file/d/1N3aJslYG4SGIb1-TvI4dg-d-fbD5yPEm/view?usp=shari [...] Format de la ressource électronique : Text Classification & Translation Using Transfer Learning and Transformers [texte imprimé] / Mafaza, Chabane, Auteur ; Abdelouahab Moussaoui, Directeur de thèse . - [S.l.] : Setif:UFA, 2021 . - 1 vol (91 f .) ; 29 cm.
Langues : Anglais (eng)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Natural language processing
Deep learning
Text classificationIndex. décimale : 004 - Informatique Résumé :
Natural language processing is field of study that focus on building machine learning models
that can read, understand and even generate human language efficiently.
Recently, There have been huge advance and progress in the field of Natural language processing
NLP to bring efficient language models that can understand and process the huge amount of
generated textual data. The Attention mechanism and the Transformer model play a role model,
where recent studies revealed that they achieved higher performance in all NLP tasks.
This work presents a detailed study on recent advances in the field of deep learning applied
to Natural language processing, mainly in Text classification and Neural machine Translation
tasks.
In this work, 10 models in total were replicated and developed then trained and validated on
2 datasets for both Single and Multi label classification, and 2 Machine translation datasets (
Arabic-English and French-English). The experiments show that Transformer based models tend
to give better performance for both Text classification and Machine translation tasks.Côte titre : MAI/0551 En ligne : https://drive.google.com/file/d/1N3aJslYG4SGIb1-TvI4dg-d-fbD5yPEm/view?usp=shari [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0551 MAI/0551 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible