Chinese text abstract generation system and method

A technique for generating systems and abstracts, used in special data processing applications, instruments, electrical digital data processing, etc.

Active Publication Date: 2017-07-04
南京云思创智信息科技有限公司
View PDF3 Cites 62 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

None of these prior art solutions

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 text abstract generation system and method
  • Chinese text abstract generation system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Such as figure 1 and figure 2 As shown, the Chinese text abstract generation system of the present embodiment includes a preprocessing module, a vocabulary understanding module, a sentence understanding module, a paragraph understanding module and an abstract automatic generation module, wherein:

[0036] The preprocessing module is used to segment the original text into words, and each vocabulary obtained after the word segmentation forms an original word vector, and arranges in order to obtain the original word vector set W={w iw |iw=1,2,...,n w},w iw Indicates the i-th word vector, n w Indicates the total number of word vectors; wherein, word segmentation specifically adopts the word segmentation method in the prior art, and the method in which all words form the original word vector is also a prior art method, such as the CBOW model.

[0037] The vocabulary comprehension module is used to convert the original word vector w of each vocabulary iw As a neural uni...

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 text abstract generation system, which comprises a preprocessing module, a vocabulary comprehension module, a sentence comprehension module, a paragraph comprehension module and an automatic generation module of an abstract, wherein the preprocessing module is used for carrying out word segmentation and the formation of an original word vector; the vocabulary comprehension module, the sentence comprehension module and the paragraph comprehension module are independently used for adopting a long and short memory to carry out bidirectional deep understanding on vocabularies, sentences and paragraphs; the automatic generation module of the abstract is used for adopting seg2seq to generate the abstract according to the word vector, a sentence vector and a paragraph vector comprehended by the vocabulary comprehension module, the sentence comprehension module and the paragraph comprehension module. The invention also discloses a Chinese text abstract generation method. By use of the Chinese text abstract generation system and method, a neural network is used for enabling a machine to truly read a full text, the comprehended text is expressed in a neural network, and a brief abstract is output in a serialized way. When the system comprehends an article, in addition to semantics, the structural representation of the article is combined to more elaborately comprehend the full text.

Description

technical field [0001] The invention relates to the technical field of text data processing, in particular to a system and method for generating Chinese text summaries. Background technique [0002] Text summarization and summarization is a scientific and technical problem that has recently emerged with big data. Because with the explosive generation of data, especially text data, people have been unable to browse and understand all relevant texts of interest in time, but the omission of some important text information will cause a lot of organizational and application losses. Therefore, the automatic summarization of text summarization is a technology that is very much needed in practical applications and has a very wide range of applications. For example, summarizing user comments on merchants and generating automatic news summaries. [0003] At present, most of the automatic generation tools for Chinese article abstracts work by extracting keyword-based fragments to for...

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): G06F17/30G06F17/27
CPCG06F16/345G06F40/30
Inventor 俞旸凌志辉
Owner 南京云思创智信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap