Character-Level Attention Convolutional Neural Networks for Short-Text Classification

This paper proposes a character-level attention convolutional neural networks model (ACNN) for short-text classification task. The model is implemented on the deep learning framework which named tensorflow. The model can achieve better short-text classification result. Experimental datasets are from three different categories and scales. ACNN model are compared with traditional model such as LSTM and CNN. The experimental results show that ACNN model significantly improves the short-text classification results.