Automatic text classification method

Abstract

The invention provides an automatic text classification method, and aims at improving the correctness and anti-noise capacity of text classification. The method comprises the following steps of: obtaining a to-be-classified text; constructing a denoising deep neural network model by adoption of a denoising automatic encoder and a restricted Boltzmann machine; carrying out feature extraction on theobtained to-be-classified text by utilizing the constructed denoising deep neural network model; and carrying out automatic classification by utilizing a Softmax regression algorithm according to thefeature extraction result. The method relates to the field of text classification.

Description

technical field [0001] The invention relates to the field of text classification, in particular to an automatic text classification method. Background technique [0002] In network information, text occupies an important position as the main information bearing way. Text classification (Text Classification, TC) is to use computers to automatically classify and mark text sets or other entities and objects according to certain classification systems or standards. At present, deep learning has been successfully applied to a variety of pattern classification problems. Using deep learning-based methods can better mine the complex semantic relationships contained in text. [0003] However, in the prior art, a single method is generally used to classify texts, which has weak feature extraction ability and poor processing ability for noise data, resulting in low accuracy of classification results. Contents of the invention [0004] The technical problem to be solved by the prese...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an automatic text classification method to solve the problems of poor noise processing ability and weak feature extraction ability existing in the prior art

Images