Evaluating Text GANs as Language Models

Generative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of ``exposure bias''. However, A major hurdle for understanding the potential of GANs for text generation is the lack of a cle...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-03
Hauptverfasser:	Tevet, Guy, Habib, Gavriel, Shwartz, Vered, Berant, Jonathan
Format:	Artikel
Sprache:	eng
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!