A cognitive neural model of executive functions in natural language processing

GOLOSIO, BRUNO;MASALA, GIOVANNI LUCA CHRISTIAN
2015-01-01

Abstract

Although extensive research has been devoted to cognitive models of human language, the role of executive functions in language processing has little been explored. In this work we present a neural-network-based cognitive architecture which models the development of the procedural knowledge that underpin language processing. The large scale organization of the architecture is based on a multi-component working memory model, with a central executive that controls the flow of information among the slave systems through neural gating mechanisms. The system was validated, starting from a tabula rasa condition, on a on a corpus of five datasets, each devoted to a thematic group, based on literature on early language assessment, at the level of a preschool child. The results show that the system is capable of learning different word classes, and to use them in expressive language, through an open-ended incremental learning process, expressing a broad range of language processing functionalities.
2015
Inglese
Procedia Computer Science
Elsevier
71
196
201
6
http://www.sciencedirect.com/science/journal/18770509
6th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2015
Esperti anonimi
2015
Lyon, France
internazionale
scientifica
Cognitive architectures; Hebbian learning rule; Human language understanding; Large-scale artificial neural networks; Verbal working memory; Computer science (all)
4 Contributo in Atti di Convegno (Proceeding)::4.1 Contributo in Atti di convegno
Golosio, Bruno; Cangelosi, Angelo; Gamotina, Olesya; Masala, GIOVANNI LUCA CHRISTIAN
273
4
4.1 Contributo in Atti di convegno
reserved
info:eu-repo/semantics/conferencePaper
File in questo prodotto:
File Dimensione Formato  
ProcediaCompSci2015.pdf

Solo gestori archivio

Tipologia: versione editoriale
Dimensione 651.03 kB
Formato Adobe PDF
651.03 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Questionario e social

Condividi su:
Impostazioni cookie