Abstractive Text Classification Using Sequence-to-convolution Neural Networks
This work addresses text classification for NLP applications, but it appears incremental as it builds on existing CNN-based methods with a new training scheme.
The authors tackled text classification by proposing Seq2CNN, a model that handles variable-length texts without preprocessing, and achieved significant accuracy improvements over word-based TextCNN.
We propose a new deep neural network model and its training scheme for text classification. Our model Sequence-to-convolution Neural Networks(Seq2CNN) consists of two blocks: Sequential Block that summarizes input texts and Convolution Block that receives summary of input and classifies it to a label. Seq2CNN is trained end-to-end to classify various-length texts without preprocessing inputs into fixed length. We also present Gradual Weight Shift(GWS) method that stabilizes training. GWS is applied to our model's loss function. We compared our model with word-based TextCNN trained with different data preprocessing methods. We obtained significant improvement in classification accuracy over word-based TextCNN without any ensemble or data augmentation.