Cargando…
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, t...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8984258/ https://www.ncbi.nlm.nih.gov/pubmed/35401316 http://dx.doi.org/10.3389/fpsyg.2022.741321 |
_version_ | 1784682145968553984 |
---|---|
author | Pannitto, Ludovica Herbelot, Aurelie |
author_facet | Pannitto, Ludovica Herbelot, Aurelie |
author_sort | Pannitto, Ludovica |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-8984258 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-89842582022-04-07 Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? Pannitto, Ludovica Herbelot, Aurelie Front Psychol Psychology 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. Frontiers Media S.A. 2022-03-23 /pmc/articles/PMC8984258/ /pubmed/35401316 http://dx.doi.org/10.3389/fpsyg.2022.741321 Text en Copyright © 2022 Pannitto and Herbelot. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Psychology Pannitto, Ludovica Herbelot, Aurelie Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? |
title | Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? |
title_full | Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? |
title_fullStr | Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? |
title_full_unstemmed | Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? |
title_short | Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition? |
title_sort | can recurrent neural networks validate usage-based theories of grammar acquisition? |
topic | Psychology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8984258/ https://www.ncbi.nlm.nih.gov/pubmed/35401316 http://dx.doi.org/10.3389/fpsyg.2022.741321 |
work_keys_str_mv | AT pannittoludovica canrecurrentneuralnetworksvalidateusagebasedtheoriesofgrammaracquisition AT herbelotaurelie canrecurrentneuralnetworksvalidateusagebasedtheoriesofgrammaracquisition |