Text feature extraction based on stacked variational autoencoder

This paper presents a text feature extraction model based on stacked variational autoencoder (SVAE). A noise reduction mechanism is designed for variational autoencoder in input layer of text feature extraction to reduce noise interference and improve robustness and feature discrimination of the mod...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Microprocessors and microsystems Ročník 76; s. 103063
Hlavní autori: Che, Lei, Yang, Xiaoping, Wang, Liang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Kidlington Elsevier B.V 01.07.2020
Elsevier BV
Predmet:
Computer architecture
Deep stack
Feature extraction
Model accuracy
Noise reduction
Text feature extraction
Variational autoencoder
Variational autoencoder
Deep stack
Text feature extraction
Noise reduction
ISSN:0141-9331, 1872-9436
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper presents a text feature extraction model based on stacked variational autoencoder (SVAE). A noise reduction mechanism is designed for variational autoencoder in input layer of text feature extraction to reduce noise interference and improve robustness and feature discrimination of the model. Three kinds of deep SVAE network architectures are constructed to improve ability of representing learning to mine feature intension in depth. Experiments are carried out in several aspects, including comparative analysis of text feature extraction model, sparse performance, parameter selection and stacking. Results show that text feature extraction model of SVAE has good performance and effect. The highest accuracy of SVAE models of Fudan and Reuters datasets is 13.50% and 8.96% higher than that of PCA, respectively.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0141-9331
1872-9436
DOI:10.1016/j.micpro.2020.103063