Abstract: We proposed a short text classification model based on improved convolutional neural network. Firstly, different coding methods were used to map short text to distributed representation in different spaces, and digital features of different granularities were extracted as multi-channel inputs of short text classification model. Extracting concept features from standard knowledge base as prior knowledge to improve the semantic representation ability of short text. Secondly, the selfcoding learning strategy was added to the full connection layer, on the basis of approximate identity, the digital features were further combined to simulate the relevance within the data. Finally, the principle of relative entropy were used to increase the sparsity limit of the model, reduce the complexity and improve the generalization ability of the model. The effectiveness of the proposed model was verified by short text classification experiments on the open source dataset.

Key words: convolutional neural network, short text, concept distributed representation, sparsity, selfcoding