Journal:Applied Intelligence
Abstract:In the paper, we propose a variant of Variational Autoencoder (VAE) for sequence generation task, called SeqVAE, which is a combination of recurrent VAE and policy gradient in reinforcement learning. The goal of SeqVAE is to reduce the deviation of the optimization goal of VAE, which we achieved by adding the policy-gradient loss to SeqVAE. In the paper, we give two ways to calculate the policy-gradient loss, one is from SeqGAN and the other is proposed by us. In the experiments on them, our proposed method is better than all baselines, and experiments show that SeqVAE can alleviate the ......
Indexed by:Journal paper
First Author:Ting Gao
All the Authors:Fanyu Ding
Correspondence Author:Yidong Cui
Document Type:J
ISSN No.:1573-7497
Translation or Not:no
Date of Publication:2021-04-21
Included Journals:SCI
Links to published journals:https://doi.org/10.1007/s10489-021-02374-7