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.
Pannitto L., Herbelot A. (2022). Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition?. FRONTIERS IN PSYCHOLOGY, 13, 1-6 [10.3389/fpsyg.2022.741321].
Can Recurrent Neural Networks Validate Usage-Based Theories of Grammar Acquisition?
Pannitto L.
Primo
;
2022
Abstract
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.| File | Dimensione | Formato | |
|---|---|---|---|
|
rnn_review_final.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione
279.72 kB
Formato
Adobe PDF
|
279.72 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
