Skip to Main content Skip to Navigation
New interface
Conference papers

Recommandation d'âge pour des textes

Abstract : This paper studies a first attempt to predict an age recommendation from which a text can beunderstood by a child. As such, we first exhibits features derived from various scientific domains,then propose different architectures of neural network and compare them on a dataset of French textsdedicated to young or adult audiences. To circumvent the lack of data, we study the idea to predictages at the sentence level. The experiments show that this strong assumption leads to good results yet,better than those provided by psycholinguists, even when shifting isolated sentences to full texts.
Document type :
Conference papers
Complete list of metadata

Cited literature [27 references]  Display  Hide  Download
Contributor : Sylvain Pogodalla Connect in order to contact the contributor
Submitted on : Tuesday, June 23, 2020 - 12:01:33 PM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM


Publisher files allowed on an open archive


  • HAL Id : hal-02784764, version 3


Alexis Blandin, Gwénolé Lecorvé, Delphine Battistelli, Aline Étienne. Recommandation d'âge pour des textes. 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles, 2020, Nancy, France. pp.164-171. ⟨hal-02784764v3⟩



Record views


Files downloads