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...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Kun Zhao, Hongwei Ding, Kai Ye, Xiaohui Cui
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2021-09-01
Edice:	Entropy
Témata:	Variational AutoEncoder text generation Hidden Markov Model Transformer latent variables
On-line přístup:	https://www.mdpi.com/1099-4300/23/10/1277
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!