Text processing method and device

Abstract

The invention relates to a text processing method and device. The method comprises the steps of performing word segmentation processing on a to-be-processed first text, and determining a plurality ofwords of the first text; removing a word from the first text to obtain a second text; removing each word in the first text one by one to obtain a second text set; analyzing the first text and each second text in the second text set to obtain a first tree structure of the first text and a second tree structure of each second text; and determining the abstract text of the first text according to thefirst tree structure and the second tree structure. According to the text processing method disclosed by the embodiment of the invention, the second text corresponding to each word can be obtained bydeleting each word in the first text, so that the probability of ignoring key information is reduced. A tree structure composed of words is obtained and can comprise the word order and the syntacticstructure of the first text and the second text, and the obtained abstract text is smooth in semantics.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular to a text processing method and device. Background technique [0002] In related technologies, methods such as graph sorting and deep learning are usually used to extract abstract text from text that can express the gist information of the text and whose length is required to be smaller than the length of the original text information. The graph sorting method can filter out redundant text by using commonly used information such as stop words, suffixes, or parts of speech, but the graph sorting method tends to ignore key information, and does not consider information such as word order and syntactic structure, and the obtained summary text may not be smooth , has certain limitations. The deep learning method needs to use a large amount of labeled data to train the deep learning model, and determine the statistical information of words and abstract text based on the label...

AI Technical Summary

Problems solved by technology

The graph sorting method can filter out redundant text by using commonly used information such as stop words, suffixes, or parts of speech, but the graph sorting method tends to ignore key information, and does not consider information such as word order and syntactic structure, and the obtained summary text may not be smooth , with certain limitations

The deep learning method needs to use a large amount of labeled data to train the deep learning model, and determine the statistical information of the words based on the labels in the context, and determine the summary text. This method also does not consider information such as word order and syntactic structure.

Images