Attribute Feature Classification of English Grammar Entry Base Based on Support Vector Machine Classification Algorithm

Abstract

An attribute feature classification method of English grammar vocabulary entry database based on support vector machine classification algorithm is proposed; this method takes news English as the research object and focuses on the classification of attributes and features of the English grammar lexicon database. First, the k-means algorithm is used to cluster the training set, and the one-to-many method is used to train two types of classifiers for the texts that cannot be correctly clustered in each class, that is, the classifiers of the corresponding categories are trained, and then the training set passed through a pair of the classifier generated by multiple SVMs is tested, and the samples that fall in the inseparable area are retrained by a one-to-one method, so as to achieve the purpose of balancing the training samples and reducing the inseparable area. The results show that, compared with the FDAGSVM algorithm, the proposed three multiclass classification algorithms have significantly improved classification speed and classification accuracy, and the macro average accuracy rates are 77.94%, 73.94%, and 72.36%, respectively. While ensuring the classification speed and classification accuracy of the single-label samples, the multiclass classification is realized, and it has high accuracy, recall rate, and value, which better solves the multiclass classification problem and expands the classification capability of the support vector machine. In addition, a comprehensive index based on the SVM classification algorithm is proposed to ensure the specialization of the attribute feature classification.