Character-level nested deep network-based text classification method

Abstract

The invention relates to a character-level nested deep network-based text classification method. The method comprises the following steps of S1, constructing a character vector matrix table; S2, performing short text preprocessing; S3, extracting high-dimensional sequence features by improved Resnet; and S4, performing LSTM network classification. The character level-based text conversion can effectively perform conversion on all texts; compared with a conventional vector space model, the dimension is reduced remarkably; all the texts can be effectively converted; and low-frequency words are not ignored. In addition, the improved Resnet can self-learn a feature extraction method; and compared with conventional methods such as a TF-IDF formula, a mutual information quantity, an informationgain, an x2 statistical quantity and the like, the extracted features are more effective and abstract. Finally, the LSTM network classification can consider a sequence relationship between the words,so that the text classification can be performed more accurately.

Description

technical field [0001] The invention relates to the technical field of text classification, in particular to a character-level text classification method based on a nested deep network. Background technique [0002] With the continuous development of network technology, the Internet generates massive unstructured text data every day. In order to obtain useful value from these massive data, we need to classify these texts. [0003] Early text classification mainly classifies texts by manually defining some rules. This method is time-consuming and laborious, and one must have sufficient understanding of a certain field to write appropriate rules. With the emergence of a large number of online texts and the rise of machine learning, large-scale text (including web page) classification and retrieval has aroused researchers' interest again. The text classification system first establishes a discriminant rule or classifier by training on a pre-classified text set, so as to automa...

AI Technical Summary

Problems solved by technology

[0005] As can be seen from the above, the selection of text features occupies a very important part in text classification, and the text representation of the main problem of traditional methods is high-dimensional and sparse, and the feature expression ability is very weak, and the traditional text classification method does not consider To the relationship between words and unfriendly to low-frequency words

Images