Visually Grounded Speech Models have a Mutual Exclusivity Bias

When children learn new words, they employ constraints such as the mutual exclusivity (ME) bias: a novel word is mapped to a novel object rather than a familiar one. This bias has been studied computationally, but only in models that use discrete word representations as input, ignoring the high vari...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-03
Hauptverfasser:	Nortje, Leanne, Oneaţă, Dan, Matusevych, Yevgen, Kamper, Herman
Format:	Artikel
Sprache:	eng
Schlagworte:	Bias Speech Words (language)
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!