ResLCNN model-based short text classification method

Abstract

The invention discloses a ResLCNN model-based short text classification method, relates to the technical field of text mining and deep learning, and in particular to a deep learning model for short text classification. According to the method, characteristics of a long-short term memory network and a convolutional neural network are combined to build a ResLCNN deep text classification model for short text classification. The model comprises three long-short term memory network layer and one convolutional neural network layer; and through using a residual model theory for reference, identity mapping is added between the first long-short term memory network layer and the convolutional neural network layer to construct a residual layer, so that the problem of deep model gradient missing is relieved. According to the model, the advantage, of obtaining long-distance dependency characteristics of text sequence data, of the long-short term memory network and the advantage, of obtaining localfeatures of sentences through convolution, of the convolutional neural network are effectively combined, so that the short text classification effect is improved.

Description

technical field [0001] The invention relates to the fields of text mining and deep learning, in particular to a deep learning model for short text classification. Background technique [0002] Short text classification is a key task in natural language processing, which can help users discover useful information from massive data. The purpose of the sentence model is to learn text features to represent sentences. It is a key model for short text classification and is of great significance for tasks such as emotion recognition, question answering systems, and translation. [0003] Traditional sentence models use the bag-of-words model. Based on the vector space model representation method, sentences and documents are regarded as unordered word collections, and each feature word is independent of each other. The model does not contain word order and grammatical information, and generally has problems such as dimension disaster and sparseness. Therefore, with the continuous i...

AI Technical Summary

Problems solved by technology

This is mainly because the error cannot be effectively back-propagated to the upper network, so that the parameters of the upper network cannot be fully optimized.

Images