Multivariate feature fusion Chinese text classification method based on attention neural network

Abstract

The solution of the invention discloses a multi-feature fusion Chinese text classification method based on an Attention neural network, which belongs to the field of natural language processing. In order to further improve the accuracy of Chinese text classification, the present invention fully excavates the characteristics of text data under three different sizes of convolution kernel granularity by fusing three CNN paths; embodies the interconnection between text data by fusing LSTM paths; especially Ground, by fusing the proposed Attention algorithm model, relatively important data features can play a greater role in the process of Chinese text category recognition, thereby improving the model's ability to identify Chinese text categories. The experimental results show that under the same experimental conditions, compared with the CNN model, the LSTM structure model and the combined model of the two, the Chinese text classification accuracy of the model proposed by the present invention is significantly improved, and can be better applied to the classification accuracy The demanding field of Chinese text classification.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a multi-feature fusion Chinese text classification method based on Attention neural network. Background technique [0002] Chinese text classification is an important means to efficiently manage and mine massive Chinese text information on the Internet, and it is an important research direction in natural language processing. Since the 1990s, many researchers have begun to apply various statistical methods and machine learning methods to automatic text classification, such as support vector machine SVM, AdaBoost algorithm, naive Bayesian algorithm, KNN algorithm and Logistic regression, etc. In recent years, with the rapid development of deep learning and various neural network models, text classification methods based on deep learning have attracted close attention and research from academia and industry. Some typical neural network models, such as long short-term memo...

AI Technical Summary

Problems solved by technology

Existing research and applications have proved that LSTM (long-term short-term memory network) is suitable for learning the long-term dependencies between language units in sentences, and CNN (convolutional neural network) is suitable for learning local features of sentences, but the current research has not Fully combine the advantages of the three algorithms

Images