English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semisupervised text classification has become a major focus of research overthe past few years. Hitherto, most of the research has been based on supervisedlearning, but its main drawback is the unavailability of labeled data samplesin practical applications. It is still a key challenge to train the deepgenerative models and learn comprehensive representations without supervision.Even though continuous latent variables are employed primarily in deep latentvariable models, discrete latent variables, with their enhancedunderstandability and better compressed representations, are effectively usedby researchers. In this paper, we propose a semisupervised discrete latentvariable model for multi-class text classification and text generation. Theproposed model employs the concept of transfer learning for training aquantized transformer model, which is able to learn competently using fewerlabeled instances. The model applies decomposed vector quantization techniqueto overcome problems like posterior collapse and index collapse. Shannonentropy is used for the decomposed sub-encoders, on which a variableDropConnect is applied, to retain maximum information. Moreover, gradients ofthe Loss function are adaptively modified during backpropagation from decoderto encoder to enhance the performance of the model. Three conventional datasetsof diversified range have been used for validating the proposed model on avariable number of labeled instances. Experimental results indicate that theproposed model has surpassed the state-of-the-art models remarkably.

Entropy optimized semi-supervised decomposed vector-quantized  variational autoencoder model based on transfer learning for multiclass text  classification and generation