Extracting tags from large raw texts using End-to-End memory networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Extracting tags from large raw texts using End-to-End memory networks

Résumé

Recently, new approaches based on Deep Learning have demonstrated good capacities to manage Natural Language Processing problems. In this paper, after selecting the End-to-End Memory Networks approach for its ability to efficiently capture context meanings, we study its behavior when facing large semantic problems (large texts, large vocabulary sets) and apply it to automatically extract tags from a website. A new data set is proposed, results and parameters are discussed. We show that the so formed system can capture the correct tags most of the time, and can be an efficient and advantageous way to complement other approaches because of its ability for generalization and semantic abstraction.
Fichier principal
Vignette du fichier
paper.pdf (362.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01591669 , version 1 (21-09-2017)
hal-01591669 , version 2 (22-09-2017)
hal-01591669 , version 3 (25-09-2017)

Identifiants

  • HAL Id : hal-01591669 , version 3

Citer

Feras Al Kassar, Frédéric Armetta. Extracting tags from large raw texts using End-to-End memory networks. 2nd Workshop on Semantic Deep Learning (SemDeep-2) in the 12th International Conference on Computational Semantics (IWCS 2017), Sep 2017, Montpellier, France. pp.33-47. ⟨hal-01591669v3⟩
419 Consultations
183 Téléchargements

Partager

Gmail Facebook X LinkedIn More