Hybrid neural network text classification method capable of blending abstract with main characteristics

Abstract

The invention relates to a hybrid neural network text classification method capable of blending an abstract with main characteristics. The method comprises the following steps that: step A: extractingan abstract from each text in a training set; step B: using a convolutional neural network to learn the key local features of the abstract obtained in the step A; step C: using a long short-term memory network to learn context time sequence characteristics on the main content of each text in the training set; step D: carrying out cascade connection on two types of characteristics obtained in thestep B and the step C to obtain the integral characteristics of the text, inputting the integral characteristics of each text in the training set into a full connection layer, using a classifier to calculate a probability that each text belongs to each category to train a network, and obtaining a deep neural network model; and step E: utilizing the trained deep neural network model to predict thecategory of a text to be predicted, and outputting the category with a highest probability as a prediction category. The method is favorable for improving text classification accuracy based on the deep neural network.

Description

technical field [0001] The invention relates to the fields of natural language processing and data mining, in particular to a hybrid neural network text classification method which combines abstract and subject features. Background technique [0002] Text classification (text categorization) technology is an important basis for information retrieval and text mining, and its main task is to determine its category according to the text content under the pre-given set of category labels (label). Text classification has a wide range of applications in natural language processing and understanding, information organization and management, content information filtering and other fields. In recent years, the research idea of ​​using deep learning to build a language model has gradually matured, which has greatly improved the feature quality of the text. Some scholars first proposed a sentence classification model based on convolutional neural network, which extracts features from ...

AI Technical Summary

Problems solved by technology

[0003] At present, the deep neural network model for the document level generally uses the words in the document to form a sentence, and the sentence forms a hierarchical structure of the document to build the network model. However, these models do not take into account the obvious organizational structure of some specific documents in the text. Features, for example, the text can usually be divided into the organizational structure of the article such as the abstract, the main body, etc., and different article structures have different effects on the text category: the text abstract part is a high-level summary of the text content, which contains the main body of the event, the event The key information such as the results of the content; the main body of the text details the content, describes the cause of the content, and has the characteristics of context and timing

At present, the deep neural network model for the document level generally directly inputs the entire text into the network for unified processing, and cannot make good use of the role of different organizational structures of the text.

Images