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

Emmanuel Dupoux (1, 2)

1 LSCP - Laboratoire de sciences cognitives et psycholinguistique
2 CoML - Apprentissage machine et développement cognitif

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.

Mots clés: Artificial intelligence; Computational modeling; Early language acquisition; speech; psycholinguistics; compu-tational modeling; corpus analysis; early language acquisi-tion; infant development; language bootstrapping; machine learning

Domaines: Intelligence artificielle [cs.AI]; Linguistique; Sciences cognitives

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