Semisupervised Text Classification by Variational Autoencoder

Semisupervised text classification has attracted much attention from the research community. In this paper, a novel model, the semisupervised sequential variational autoencoder (SSVAE), is proposed to tackle this problem. By treating the categorical label of unlabeled data as a discrete latent varia...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transaction on neural networks and learning systems Ročník 31; číslo 1; s. 295 - 308
Hlavní autoři: Xu, Weidi, Tan, Ying
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.01.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Classification
Data models
Decoders
Decoding
Feature extraction
Generative models
Lower bounds
Mathematical analysis
Performance enhancement
Predictive models
Semisupervised learning
Task analysis
text classification
Training
variational autoencoder (VAE)
ISSN:2162-237X, 2162-2388, 2162-2388
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Semisupervised text classification has attracted much attention from the research community. In this paper, a novel model, the semisupervised sequential variational autoencoder (SSVAE), is proposed to tackle this problem. By treating the categorical label of unlabeled data as a discrete latent variable, the proposed model maximizes the variational evidence lower bound of the data likelihood, which implicitly derives the underlying label distribution for the unlabeled data. Analytical work indicates that the autoregressive nature of the sequential model is the crucial issue that renders the vanilla model ineffective. To remedy this, two types of decoders are investigated in the SSVAE model and verified. In addition, a reweighting approach is proposed to circumvent the credit assignment problem that occurs during the reconstruction procedure, which can further improve performance for sparse text data. Experimental results show that our method significantly improves the classification accuracy compared with other modern methods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2019.2900734