Assessing BERT’s ability to learn Italian syntax: a study on null-subject and agreement phenomena

The work presented in this paper investigates the ability of BERT neural language model pretrained in Italian to embed syntactic dependency relationships into its layers, by approximating a Dependency Parse Tree. To this end, a structural probe, namely a supervised model able to extract linguistic s...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of ambient intelligence and humanized computing Jg. 14; H. 1; S. 289 - 303
Hauptverfasser:	Guarasci, Raffaele, Silvestri, Stefano, De Pietro, Giuseppe, Fujita, Hamido, Esposito, Massimo
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2023 Springer Nature B.V
Schlagworte:	Artificial Intelligence Computational Intelligence Engineering English language Italian language Knowledge Linguistics Machine translation Morphology Natural language Original Research Parsers Robotics and Automation Semantics Syntax User Interfaces and Human Computer Interaction Neural language model Structural probe Syntactic phenomena Dependency parse tree
ISSN:	1868-5137, 1868-5145
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!