Large-Scale Text Classification Method Based on Deep Topic Model

Abstract

The invention discloses a text analysis method based on a deep topic model, which mainly solves the problems in the prior art that the gradient cannot be solved and the gradient update steps of each layer cannot be adjusted. The main steps are: 1. Establish a training set and a test set; 2. Set the Poisson-Gamma confidence network and its parameters, and use the training set in step 1 to perform gradient update training on the network; 3. Save the trained network overall Parameters; 4. Use the global parameter values ​​saved in step 3 to initialize the global parameters of the test network, and use the test set in step 1 to train the test network; 5. Save the network parameters of the test network; 6. Use the test network parameters obtained in step 5 Classify the text and output the predicted text category and text classification accuracy. The invention can extract multi-layer information of text information, solves the problems that the gradient is difficult to solve and the step length of each layer cannot be adjusted, and can be used for text information extraction and text classification.

Description

technical field [0001] The invention belongs to the technical field of text processing, and in particular relates to a large-scale text classification method of a deep topic model based on adaptive step size stochastic gradient training, which can be used for text data mining and classification. Background technique [0002] At present, the topic models used in the field of natural language processing are not only more and more, but also more and more mature, but there are differences in training methods and practicability. Although some shallow models are more practical, But it is not as good as the deep model in performance. For example, the commonly used LDA topic model is one of them. Although the performance of the deep topic model is improved compared with the shallow topic model, because of its complicated training, the training time is too long, especially When the data set is particularly large, it is lacking in practicability, such as the Poisson-Gamma Belief Netwo...

AI Technical Summary

Problems solved by technology

At present, the stochastic gradient method is mostly applied to the shallow model. For the deep model, the stochastic gradient method is rarely applied, not only because there is a large correlation between the layers of the deep model, the gradient calculation is very complicated; and in During the training process of the deep topic model trained by the stochastic gradient method, the gradient update step size between layers cannot be adjusted

Images