Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chinese abstract generation method based on component syntactic analysis

A syntactic analysis and abstract technology, applied in the field of information processing, can solve the problems of unclear abstract subject and low readability, and achieve the effect of solving the problem of accuracy and readability.

Pending Publication Date: 2022-06-03
CENT SOUTH UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the prior art, the present invention provides a Chinese abstract generation method, device and storage medium based on component syntactic analysis to solve the problem of unclear gist and poor readability of the abstract obtained by the existing text abstract generation method. high problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Chinese abstract generation method based on component syntactic analysis
  • Chinese abstract generation method based on component syntactic analysis
  • Chinese abstract generation method based on component syntactic analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044]In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other implementations obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0045] like figure 1 As shown, an embodiment of the present invention discloses a method for generating Chinese abstracts based on component syntax analysis, including:

[0046] S1: Preprocess the document to be generated to obtain a text sentence set.

[0047] Specifically, each sentence in the document is filtered out of stop words in turn, and only words with the specified part of speech are retained, thereby obtaining a new set of text sentences.

[0048] S2: Based on the text ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a Chinese abstract generation method based on component syntactic analysis, and the method comprises the steps: carrying out the preprocessing of a document, and obtaining a text sentence set; based on the text sentence set, using a semantic extraction model to obtain text semantic information codes; based on the text sentence set, generating a component syntactic analysis structure tree of each sentence, and converting the component syntactic analysis structure tree of each sentence into a component syntactic structure serialization code based on a span method; jointly inputting the text semantic information codes and the component syntactic structure serialization codes into an encoder for integration coding; and decoding the integrated code transmitted by the encoder through a decoder to generate a text abstract. The original grammar structure of the text can be proposed to supervise the text abstract generation process, and the accuracy problem and the readability problem of the text abstract are solved.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method for generating Chinese abstracts based on component syntax analysis. Background technique [0002] The National Natural Science Foundation of China includes the application of basic theory and applied basic theory research work, which is a theoretical work to reveal the universal laws, basic principles and nature of natural phenomena. In the process of applying for fund declarations, review experts need to efficiently and accurately obtain valid information from the texts of massive declarations, and make a review. Text summarization technology aims to automatically extract key information from a large number of application text data, which can play an auxiliary role in the expert review process to a certain extent. However, a large number of scientific research terminology are included in the fund application form. It is difficult for the existing text s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/211G06F40/30G06N3/04G06N3/08
CPCG06F40/211G06F40/30G06N3/08G06N3/047G06N3/045
Inventor 龙军李浩然刘磊向一平
Owner CENT SOUTH UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products