Measuring text readability with machine comprehension: a pilot study - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Measuring text readability with machine comprehension: a pilot study

Marc Benzahra
  • Fonction : Auteur
  • PersonId : 1052435
François Yvon

Résumé

This article studies the relationship between text readability indice and automatic machine understanding systems. Our hypothesis is that the simpler a text is, the better it should be understood by a machine. We thus expect to a strong correlation between readability levels on the one hand, and performance of automatic reading systems on the other hand. We test this hypothesis with several understanding systems based on language models of varying strengths, measuring this correlation on two corpora of journalistic texts. Our results suggest that this correlation is rather small that existing comprehension systems are far to reproduce the gradual improvement of their performance on texts of decreasing complexity.
Fichier principal
Vignette du fichier
document(5).pdf (363.05 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02267546 , version 1 (19-08-2019)

Identifiants

  • HAL Id : hal-02267546 , version 1

Citer

Marc Benzahra, François Yvon. Measuring text readability with machine comprehension: a pilot study. Workshop on Building Educational Applications Using NLP, Aug 2019, Florence, Italy. pp.412 - 422. ⟨hal-02267546⟩
215 Consultations
287 Téléchargements

Partager

Gmail Facebook X LinkedIn More