Short text classification method based on semantic enhancement

Abstract

The invention discloses a short text classification method based on semantic enhancement. The method comprises the steps of 1, constructing a short text classifier, obtaining a short text training setrelevant to the field from internet resources, expanding corpuses and training word vectors for each short text, and training the short text classifier; 2, after expanding the corpuses and training the word vectors for each to-be-classified short text, inputting the to-be-classified short texts to the short text classifier obtained in step 1 for classification to obtain a classification result. By means of the short text classification method based on the semantic enhancement, the semantics of the short texts is enhanced and the texts are classified, aiming at the features of the short textsthat the information amount is small and the semantics is sparse, a method of expanding the corpuses with high quality and training the word vectors with high precision is utilized to conduct semanticenhancement representation on the short texts; meanwhile, an efficient text classification algorithm is utilized, the finite features of the texts are captured to the greatest extent, and the training time of the classifier is effectively shortened.

Description

technical field [0001] The invention relates to the field of computational linguistics, in particular to the field of computer natural language processing, in particular to a short text classification method based on semantic enhancement. Background technique [0002] At present, with the rapid development of the electronic technology industry, many short texts such as Weibo, comments, and WeChat are transmitted to our mobile terminals through the network every day in our lives, and these short text messages show explosive growth. In order to better cope with such a rapidly growing amount of information, text classification technology came into being. Short text has the characteristics of less text information and sparse features, so compared with long text, the realization of automatic classification of short text is more challenging. Facing this challenge, researchers have expanded the corpus of short texts due to their short content and sparse features, and then used exi...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings of the existing short text corpus expansion method that is too complicated, the quality of the expanded corpus is low, and the word vector training set is not accurate, and a relatively simple high-quality corpus expansion method is proposed, so as to perform high-quality short texts on short texts. Semantic representation performance is enhanced by quality corpus augmentation and word vector training using precise corpus

Images