Text classification is an important task in natural language processing with wide applications. Traditional text classification methods manually extract the features which are later fed into the classifier for training. Recent researchers have employed convolutional neural networks or recurrent neural networks for text classification motivated by the noticeable success of deep learning. However, most of their models are based on single 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 local features from text and also those of recurrent neural networks (LSTM) in memory to connect the extracted features. We conduct extensive experiments on two Chinese data sets and five English data sets, and compare our method with several other classification methods. Experimental results show that the proposed method can achieve better accuracy on text classification tasks.
Convolution neural network (CNN), Feature Extraction
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask,hadoop Frontend :-python Backend:- MYSQL
₹10000 (INR)
2019