Abstract Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) based
text classification algorithms currently in use can successfully extract local textual features …

Classification of texts potentially containing a complex and specific terminology requires the
use of learning methods that do not rely on extensive feature engineering. In this work we …

How to eliminate useless information in the vast network information and retain effective
information is a problem that needs to be continuously explored in the field of deep learning …

Recurrent neural network (RNN) and convolutional neural network (CNN) are two prevailing
architectures used in text classification. Traditional approaches combine the strengths of …

We propose a BERT-based data augmentation for labeled sentences called Aug-Bert. New
sentences are generated by stochastically selecting words and replacing them with other …

The CNN-LSTM model has the advantages of combining Convolutional Neural Network
(CNN) and Long-Short Term Memory (LSTM). It can perform timing analysis while extracting …

This paper proposes a simple yet effective interpolation-based data augmentation approach
termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first …

In this paper we propose a non-greedy active learning method for text categorization using
least-squares support vector machines (LSSVM). Our work is based on transductive …

A basic assumption in traditional machine learning is that the training and test data
distributions should be identical. This assumption may not hold in many situations in …

Performance of text classification models tends to drop over time due to changes in data,
which limits the lifetime of a pretrained model. Therefore an ability to predict a model's ability …