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

•Key theoretical puzzles of infant language development are still unsolved.•A roadmap for reverse engineering infant language learning using AI is proposed.•AI algorithms should use realistic input (little or no supervision, raw data).•Realistic input should be obtained by large-scale recording in e...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Cognition Ročník 173; s. 43 - 59
Hlavní autor: Dupoux, Emmanuel
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands Elsevier B.V 01.04.2018
Elsevier Science Ltd
Elsevier
Témata:
Artificial Intelligence
Building engineers
Cognition
Cognition & reasoning
Cognitive ability
Cognitive development
Cognitive science
Computational mathematics
Computational modeling
Computer applications
Computer Science
Corpus analysis
Early language acquisition
Engineering
Feasibility
Infant development
Infants
Information processing
Language
Language acquisition
Language bootstrapping
Learning algorithms
Linguistics
Machine learning
Machinery
Privacy
Psycholinguistics
Speech
Infant development
Computational modeling
Early language acquisition
psycholinguistics
Machine learning
Speech
Artificial intelligence
Language bootstrapping
Corpus analysis
early language acquisi-tion
corpus analysis
language bootstrapping
speech
compu-tational modeling
machine learning
infant development
ISSN:0010-0277, 1873-7838, 1873-7838
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Key theoretical puzzles of infant language development are still unsolved.•A roadmap for reverse engineering infant language learning using AI is proposed.•AI algorithms should use realistic input (little or no supervision, raw data).•Realistic input should be obtained by large-scale recording in ecological environments.•Machine/Human comparison should be run on a benchmark of psycholinguistic tests. 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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-0277
1873-7838
1873-7838
DOI:10.1016/j.cognition.2017.11.008