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

  title={Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner},
  author={Emmanuel Dupoux},
  • Emmanuel Dupoux
  • Published 2018
  • Computer Science, Medicine
  • Cognition
  • Spectacular progress in the information processing sciences (machine learning, wearable sensors) promises to revolutionize the study of cognitive development. [...] Key Method 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.Expand Abstract
    Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks
    • 12
    • Open Access
    Computational and Robotic Models of Early Language Development: A Review
    • 1
    • Open Access
    Are words easier to learn from infant- than adult-directed speech? A quantitative corpus-based investigation
    • 8
    • Open Access
    Learning the generative principles of a symbol system from limited examples
    The zero resource speech challenge 2017
    • 134
    • Open Access


    Publications referenced by this paper.
    Building Machines That Learn and Think Like People
    • 931
    • Open Access
    Knowledge and learning in natural language
    • 480
    • Open Access
    Child's Talk: Learning to Use Language
    • 1,890
    Foundations for a New Science of Learning
    • 542
    • Open Access
    A First Language: The Early Stages
    • 3,139
    The faculty of language: what is it, who has it, and how did it evolve?
    • 2,035
    • Open Access
    Intrinsic Motivation Systems for Autonomous Mental Development
    • 928
    • Open Access
    The acquisition of syntactic knowledge
    • 710
    • Open Access
    A computational learning model for metrical phonology
    • 300