Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers

To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations. A new line of work on improving model interpretability has just started, and many existing methods require either prior information or h...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chen, Hanjie, Ji, Yangfeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!