Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction

Neural parameterization has significantly advanced unsupervised grammar induction. However, training these models with a traditional likelihood loss for all possible parses exacerbates two issues: 1) \(\textit{structural optimization ambiguity}\) that arbitrarily selects one among structurally ambig...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-07
Hauptverfasser:	Park, Jinwook, Kim, Kangil
Format:	Artikel
Sprache:	eng
Schlagworte:	Ambiguity Bias Grammars Optimization Parameterization Sentences Variance analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!