A Transformer-Based Hierarchical Variational AutoEncoder Combined Hidden Markov Model for Long Text Generation

The Variational AutoEncoder (VAE) has made significant progress in text generation, but it focused on short text (always a sentence). Long texts consist of multiple sentences. There is a particular relationship between each sentence, especially between the latent variables that control the generatio...

Descrición completa

Detalles Bibliográficos

Principais autores:	Kun Zhao, Hongwei Ding, Kai Ye, Xiaohui Cui
Formato:	Artigo
Idioma:	Inglês
Publicado:	MDPI AG 2021-09-01
Series:	Entropy
Assuntos:	Variational AutoEncoder text generation Hidden Markov Model Transformer latent variables
Acceso en liña:	https://www.mdpi.com/1099-4300/23/10/1277
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!