Return of the RNN: Residual Recurrent Networks for Invertible Sentence Embeddings

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our approach employs a regression-based output layer to reconstruct the...

Ausführliche Beschreibung

Bibliographische Detailangaben

1. Verfasser:	Wilkerson, Jeremy
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!