Text-summarization generating method based on neural network

Abstract

The invention provides a text-summarization generating method based on a neural network. The text-summarization generating method based on the neural network includes the steps that an input documentis subjected to word segmentation and vectorization expression, and word vectors are obtained; all obtained word vectors of all sentences are input into a first layer of a first circulation neural network in sequence, and state vectors of the sentences after current word vectors of the sentences are input are obtained, wherein the state vectors of the corresponding sentences after the last word vectors of all the sentences are input represent sentence vectors of the sentences; all the sentence vectors are input into a second layer of the first circulation neural network in sequence, and corresponding document state vectors after all the sentences are input into the document are obtained, wherein the corresponding document state vector after the last sentence is input is a state vector of the whole document; expression of the input document is decoded through a second circulation neural network, and summarization is generated. According to the text-summarization generating method basedon the neural network, the cost problem when summarization is manually generated is solved, and meanwhile the information fragmentation problem and the information ambiguity problem which are caused by a sentence extraction method are solved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method for generating text summaries based on a neural network. Background technique [0002] We are in the era of information explosion. While enjoying the convenience brought by various information, people are increasingly eager to refine and condense information, express the main content and central idea with fewer words, so that Reduce time to obtain information. Although most scientific papers are accompanied by abstracts written by the authors themselves, many articles, news reports, and other written sources in the social sciences do not have manual abstracts. However, manual writing of abstracts requires a comprehensive understanding of the content of the original text, so the manual writing process of abstracts is quite time-consuming. For literature in certain professional fields, manual writing of abstracts also requires certain professional kno...

AI Technical Summary

Problems solved by technology

Although the extractive method to extract abstracts avoids the problem that people have to read through the full text to understand important information to a certain extent, it is not satisfactory in terms of content and language quality.

Because the sentences in the abstract obtained by the extraction method are only a simple patchwork of some important sentences in the original document, there is no relevance, resulting in information fragmentation and ambiguity, which ultimately leads to inaccurate understanding by users

Images