Mathematical problem text multi-label classification method based on mathematical feature extraction

Abstract

The invention discloses a mathematical problem text multi-label classification method based on mathematical feature extraction, and the method comprises the steps: taking mathematical problem test questions as samples, and taking knowledge points as sample labels; carrying out preprocessing and feature extraction on the sample and the label thereof, and coding a sample feature vector to obtain a hidden layer vector; a self-attention mechanism is cited to calculate the attention weight of each hidden layer vector, and a feature vector output by the text is obtained; dividing the answer analysis text into leaf nodes and root nodes, and forming a feature matrix of a feature priori tree by leaf node text information features and root node text information features; performing mathematical feature extraction on the sample feature vector and the feature matrix of the feature priori tree, inputting the feature vector output by the text and the output result of the mathematical feature extraction part into a classifier, and outputting a classification result by the classifier; a training stop condition is set, and when training stops, a trained mathematical text multi-label classification model is obtained; and utilizing the mathematical text multi-label classification model to effectively classify mathematical problem texts.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a multi-label text classification method for mathematical questions combined with prior knowledge and mathematical feature extraction. Background technique [0002] In recent years, with the development of computing power, the theory and application of artificial intelligence have made breakthroughs, and have been widely implemented in the fields of computer vision, natural language processing, and recommendation algorithms, and have been integrated into all aspects of daily life. For example, ubiquitous biometric recognition technology; recommendation technology integrated into various consumption scenarios; intelligent customer service, machine translation, text mining, risk control, assisted driving and other technologies have greatly changed people's lifestyles. The use of artificial intelligence technology to replace repetitive human labor and improve efficiency ha...

AI Technical Summary

Problems solved by technology

Moreover, using the method of machine learning, the model effect is greatly affected by the artificial selection of features.

There is a lot of noise, and the proportion of sparse data decreases, which leads to the disappearance of data aggregation effect and makes feature learning difficult.

Ye et al. adopted the deep learning method, combined with word vectors expressing semantic information in the field of natural language processing, to train the model to generate knowledge point labels, but the text of the math problem has a strong logic, and some derived information classifiers cannot recognize come out

Images