Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the factorization in the latent space of models such as the variational aut...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Balasubramanian, Vikash, Kobyzev, Ivan, Bahuleyan, Hareesh, Shapiro, Ilya, Vechtomova, Olga
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!