Modeling rapid language learning by distilling Bayesian priors into artificial neural networks

R. Thomas McCoy () and Thomas L. Griffiths
Additional contact information
R. Thomas McCoy: Yale University
Thomas L. Griffiths: Princeton University, South Drive

Nature Communications, 2025, vol. 16, issue 1, 1-14

Abstract: Abstract Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science. Existing approaches have been successful at explaining how humans generalize rapidly in controlled settings but are usually too restrictive to tractably handle naturalistic data. We show that learning from limited naturalistic data is possible with an approach that bridges the divide between two popular modeling traditions: Bayesian models and neural networks. This approach distills a Bayesian model’s inductive biases—the factors that guide generalization—into a neural network that has flexible representations. Like a Bayesian model, the resulting system can learn formal linguistic patterns from limited data. Like a neural network, it can also learn aspects of English syntax from naturally-occurring sentences. Thus, this model provides a single system that can learn rapidly and can handle naturalistic data.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-59957-y Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-59957-y

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-59957-y

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().