Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner

Emmanuel Dupoux 1, 2
2 CoML - Apprentissage machine et développement cognitif
LSCP - Laboratoire de sciences cognitives et psycholinguistique, Inria de Paris
Abstract : Spectacular progress in the information processing sciences (machine learning, wearable sensors) promises to revolutionize the study of cognitive development. Here, we analyse the conditions under which ’reverse engineering’ language development, i.e., building an effective system that mimics infant’s achievements, can contribute to our scientific understanding of early language development. We argue that, on the computational side, it is important to move from toy problems to the full complexity of the learning situation, and take as input as faithful reconstructions of the sensory signals available to infants as possible. On the data side, accessible but privacy-preserving repositories of home data have to be setup. On the psycholinguistic side, specific tests have to be constructed to benchmark humans and machines at different linguistic levels. We discuss the feasibility of this approach and present an overview of current results.
Type de document :
Article dans une revue
Cognition, Elsevier, 2018, 173, pp.43 - 59. 〈10.1016/j.cognition.2017.11.008〉
Liste complète des métadonnées

Littérature citée [92 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01888694
Contributeur : Emmanuel Dupoux <>
Soumis le : vendredi 7 décembre 2018 - 14:59:06
Dernière modification le : vendredi 7 décembre 2018 - 18:00:39

Fichier

1607.08723.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Emmanuel Dupoux. Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner. Cognition, Elsevier, 2018, 173, pp.43 - 59. 〈10.1016/j.cognition.2017.11.008〉. 〈hal-01888694〉

Partager

Métriques

Consultations de la notice

44

Téléchargements de fichiers

9