Discovering the Compositional Structure of Vector Representations with Role Learning Networks

How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations? We use a novel analysis technique called ROLE to show that recurrent neural networks perform well on such tasks by converging to solutions which implicitly represent symbolic...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-11
Hauptverfasser:	Soulos, Paul, McCoy, Tom, Linzen, Tal, Smolensky, Paul
Format:	Artikel
Sprache:	eng
Schlagworte:	Coders Computer Science - Computation and Language Computer Science - Learning Constituents Embedded systems Embedding Ground truth Learning Neural networks Representations Statistics - Machine Learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!