Work

A Hybrid Convolutional Variational Autoencoder for Text Generation

Year: 2017
Type: conference-paper
Abstract: In this paper we explore the effect of architectural choices on learning a variational autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid the issue of the VAE collapsing to a deterministic model.
Language: English
Open Access status: hybrid
OpenAlex ID: W2586756136
FWCI: 12
Cites: 46
Cited by: 228
Related to: 10