Method and device for representing text

Abstract

The invention discloses a method and a device for representing a text, which are used for increasing the accuracy of text representation so as to increase the accuracy of text processing. The method comprises the steps of determining all words of a current text, determining word vectors of all the words, clustering all the word vectors, determining feature words and the weight of the feature words in the current text from all the words according to a clustering result, and determining the text vector of the current text according to the word vectors and the weight of the feature words. In such a way, the semanteme of the words in sentences and a correlation between the sentences are considered in the process of determining the feature words through clustering, the connotation of the text can be accurately represented by the determined word vectors of the feature words, thus the accuracy of the text representation is increased, and the accuracy of the text processing is further increased.

Description

technical field [0001] The invention relates to information processing technology, in particular to a text representation method and device. Background technique [0002] In the field of information processing technology, text processing is often involved. Text processing refers to the processing of text retrieval, text classification, and text analysis on the text content after text representation. Among them, text representation refers to turning the original text content into the internal representation structure of the computer. The internal representation structure is a computer program. Analyzable structure, for example, words, phrases, etc. in the text content can be used to form a computer-analyzable vector structure. [0003] The higher the accuracy of text representation, the more accurately the connotation of the current text can be expressed, the better the effect of text processing and the higher the efficiency, on the contrary, the lower the accuracy of text r...

AI Technical Summary

Problems solved by technology

[0005] In the text representation method provided by the above-mentioned prior art, when selecting feature words, the semantics of the feature words in the sentence are not considered, and the correlation between sentences is not considered, but the frequency of mechanical extraction from the text is greater than the preset value. In addition, since the feature words in the text vector are words in the text, independent words may have multiple meanings and cannot accurately express the connotation of the text. Therefore, the accuracy of the text vector to express the text is low , correspondingly, the accuracy of text processing is lower

Images