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

Text classification plays an important role in many practical applications.In the real world, there are extremely small datasets. Most existing methodsadopt pre-trained neural network models to handle this kind of dataset.However, these methods are either difficult to deploy on mobile devices becauseof their large output size or cannot fully extract the deep semanticinformation between phrases and clauses. This paper proposes a multimodel-baseddeep learning framework for short-text multiclass classification with animbalanced and extremely small data set. Our framework mainly includes fivelayers: The encoder layer uses DISTILBERT to obtain context-sensitive dynamicword vectors that are difficult to represent in traditional feature engineeringmethods. Since the transformer part of this layer is distilled, our frameworkis compressed. Then, we use the next two layers to extract deep semanticinformation. The output of the encoder layer is sent to a bidirectional LSTMnetwork, and the feature matrix is extracted hierarchically through the LSTM atthe word and sentence level to obtain the fine-grained semantic representation.After that, the max-pooling layer converts the feature matrix into alower-dimensional matrix, preserving only the obvious features. Finally, thefeature matrix is taken as the input of a fully connected softmax layer, whichcontains a function that can convert the predicted linear vector into theoutput value as the probability of the text in each classification. Extensiveexperiments on two public benchmarks demonstrate the effectiveness of ourproposed approach on an extremely small data set. It retains thestate-of-the-art baseline performance in terms of precision, recall, accuracy,and F1 score, and through the model size, training time, and convergence epoch,we can conclude that our method can be deployed faster and lighter on mobiledevices.

A multi-model-based deep learning framework for short text multiclass classification with the imbalanced and extremely small data set