Short text classification method based on semantic graphs

Abstract

The invention discloses a short text classification method based on semantic graphs, which is characterized by including the steps: A, constructing a semantic graph model for each piece of text information, and combining all semantic graph models; B, comparing similarity level among different texts according to the semantic graph models and by means of a similarity computing method; and C, according to the text similarity level, classifying the texts by the aid of a text semantic graph classifier. The short text classification method based on the semantic graphs has the advantages that semantic connotations of documents can be highlighted to a maximum degree by using the graph models to represent the texts, latent semantic information and theme features in the texts can be accurately described to a great extent by the aid of the TSG (text semantic graph) models constructed by the method, and the TSG classification method can be more reliable and efficient in use as compared with other classification methods by means of the feature, so that human cost is greatly reduced, artificial arrangement of the text information is avoided to a great extent, and the text information is automatically organized by a computer.

Description

technical field [0001] The invention relates to the field of language processing, representation and text classification, in particular to a semantic graph-based short text classification method. Background technique [0002] The rapid change of Internet technology has brought human society into an era of extremely rich and rapidly updated information. Especially in recent years, with the emergence of various social networks, massive text information is continuously generated and disseminated every day. These text information are usually composed of short discourse composition. People have to deal with massive information resources every day, but using manual labor is very inefficient. Therefore, the problem we urgently need to solve is: how to make better use of the potential semantic information in the massive information on the Internet to efficiently organize and classify the text information, so as to manage and maintain the massive text more effectively. In recent ye...

AI Technical Summary

Problems solved by technology

As an effective representation method for English text, VSM has certain defects and deficiencies in the representation method of Chinese text: (1) lack of root features, the text is usually represented as a high-dimensional sparse vector; (2) the information entropy contained in different words and its There is no distinction between the contribution of the document topic; (3) the rich meaning of Chinese words makes there are not many identical words in documents with the same or similar semantics, and the natural semantic connection between concepts is lost in the text representation

But these methods are more or less flawed

Images