… • We propose a novel graph neural network method for text classification. To the best of
our knowledge, this is the first study to model a whole corpus as a heterogeneous graph and …

… convolutional neural network for text classification without … traditional window-based neural
networks. We also employ a … in text classification to capture the key components in texts. We …

… 2 Background: 1D Text Convolutions We focus on the task of text classification. We consider …
as an embedding vector, a single convolutional layer with m filters is applied, producing an …

… : using up to 29 convolutional layers, we report … text classification tasks. To the best of our
knowledge, this is the first time that very deep convolutional nets have been applied to text …

… text classification, either when character or word inputs are considered. We show on 5 standard
text classification … give better performances than shallow networks when the text input is …

… In order to test the effect of text length on training effect … texts from NetEase news and text
classification corpus of Fudan University. These texts are with lengths (word number in one text) …

… network. In this paper, we introduce a convolutional recurrent neural network for text
classification, which enjoys both the advantages of convolutional neural networks for extracting …

… -level convolutional networks (ConvNets) for text classification. We constructed several
largescale datasets to show that character-level convolutional networks could achieve state-of-the…

… Text classification is a fundamental task in NLP applications. Most existing work relied on …
Convolutional Neural Network to learn the coalesced embedding and to perform classification. …

… Inspired by the recent progress, we propose a new graphbased text classification … text
graphs are firstly constructed to form a text graph tensor. The graph tensor is used to capture text …