Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition?

It has been shown that Recurrent Artificial Neural Networks automatically acquire some grammatical knowledge in the course of performing linguistic prediction tasks. The extent to which such networks can actually learn grammar is still an object of investigation. However, being mostly data-driven, they provide a natural testbed for usage-based theories of language acquisition. This mini-review gives an overview of the state of the field, focusing on the influence of the theoretical framework in the interpretation of results.

Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? / Pannitto, L.; Herbelot, A.. - In: FRONTIERS IN PSYCHOLOGY. - ISSN 1664-1078. - 13:(2022), p. 741321. [10.3389/fpsyg.2022.741321]

Titolo: Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition?
Autori: Pannitto, L.; Herbelot, A.
Autori Unitn: 
Pannitto, Ludovica
Herbelot, Aurelie Georgette Geraldine
Titolo del periodico: FRONTIERS IN PSYCHOLOGY
Anno di pubblicazione: 2022
Codice identificativo Scopus: 2-s2.0-85128169608
Codice identificativo Pubmed: 35401316
Digital Object Identifier (DOI): http://dx.doi.org/10.3389/fpsyg.2022.741321
Handle: http://hdl.handle.net/11572/340774
Citazione: Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? / Pannitto, L.; Herbelot, A.. - In: FRONTIERS IN PSYCHOLOGY. - ISSN 1664-1078. - 13:(2022), p. 741321. [10.3389/fpsyg.2022.741321]
Appare nelle tipologie:03.1 Articolo su rivista (Journal article)

File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
 
 
 
Powered by IRIS-about IRIS-Utilizzo dei cookie
Logo CINECA  Copyright © 2022