Mama/Papa, Is this Text for Me ? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Mama/Papa, Is this Text for Me ?

Résumé

Children have less linguistic skills than adults, which makes it more difficult for them to understand some texts, for instance when browsing the Internet. In this context, we present a novel method which predicts the minimal age from which a text can be understood. This method analyses each sentence of a text using a recurrent neural network, and then aggregates this information to provide the text-level prediction. Different approaches are proposed and compared to baseline models, at sentence and text levels. Experiments are carried out on a corpus of 1, 500 texts and 160K sentences. Our best model, based on LSTMs, outperforms state-of-the-art results and achieves mean absolute errors of 1.86 and 2.28, at sentence and text levels, respectively.
Fichier principal
Vignette du fichier
Text_to_Kids_COLING2020.pdf (278.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03112352 , version 1 (16-01-2021)

Identifiants

Citer

Rashedur Rahman, Gwénolé Lecorvé, Aline Étienne, Delphine Battistelli, Nicolas Béchet, et al.. Mama/Papa, Is this Text for Me ?. International Conference on Computational Linguistics, Dec 2020, Virtuel, Spain. pp.6296-6301, ⟨10.18653/v1/2020.coling-main.554⟩. ⟨hal-03112352⟩
82 Consultations
105 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More