Text multi-label classification method and system based on attention mechanism and GCN

Abstract

The invention discloses a text multi-label classification method based on an attention mechanism and a GCN, and the method comprises the steps: obtaining a to-be-classified text, carrying out the preprocessing of the to-be-classified text, and converting the preprocessed to-be-classified text into a multi-dimensional vector through a Glove pre-training word vector; and inputting the obtained multi-dimensional vector into a pre-trained classification model to obtain a classification result of the to-be-classified text. According to the method, semantic correlation among texts, words and labels is constructed by utilizing an attention mechanism; on one hand, texts and label information are summarized to form a new text word representation form, and text feature extraction is more sufficiently carried out; on the other hand, texts and word information are summarized to form a new label representation form, and a graph neural network is used to carry out correlation modeling of the labels. And the text multi-label classification effect is improved from two angles.

Description

technical field [0001] The present invention belongs to the technical field of natural language processing, and more specifically relates to a text multi-label classification method and system based on an attention mechanism and a Graphic convolutional network (GCN for short). Background technique [0002] With the development of society and network technology, there are massive information resources in the form of text. How to effectively classify these texts and quickly, accurately and comprehensively mine effective information has become one of the hotspots in the field of natural language processing research. Text classification refers to determining a category for each document in a document collection, and there are a wide range of application scenarios. As a difficulty in the field of text classification, multi-label classification has also attracted a lot of attention. Most of the current multi-label classification methods consider two parts: [0003] 1. Feature ex...

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a text multi-label classification method and system based on attention mechanism and GCN. part, leading to technical problems that affect the accuracy of text classification, and due to the convolution operation of convolutional neural networks, it is easy to ignore the semantic relationship of text, thus affecting the technical problems of text classification accuracy, and because most of them adopt data-driven methods, It ignores the role of different parts of the text in predicting different labels, which leads to technical problems affecting the accuracy of text classification

Images