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

Automatic text abstraction method

An automatic text and abstract technology, applied in unstructured text data retrieval, text database browsing/visualization, instruments, etc., can solve problems such as semantic irrelevance and repeated abstracts

Active Publication Date: 2019-10-29
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem of abstract repetition and semantic irrelevance in the abstract generated by the existing automatic text summarization technology, and proposes an automatic text summarization method, which can filter useless text as much as possible on the basis of retaining important information of the original text information, so that the generated abstract avoids repeated abstract words and is semantically related

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
  • Automatic text abstraction method
  • Automatic text abstraction method
  • Automatic text abstraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] Exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be understood that the embodiments shown and described in the drawings are only exemplary, and are intended to illustrate the principle and spirit of the present invention, but not to limit the scope of the present invention.

[0069] The embodiment of the present invention provides an automatic text summarization method, such as figure 1 As shown, it includes the following steps S1 to S2:

[0070] S1. Globally encode the context of text information based on the convolutional neural network and self-attention mechanism, and use the information selection gate to filter the global encoding result to obtain the encoding output result.

[0071] Such as figure 2 As shown, step S1 includes the following sub-steps S11 to S14:

[0072] S11. Use a two-way LSTM network to obtain LSTM output concatenation results in two directions h i :

[0073]

[0074] a...

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 an automatic text abstraction method, and the method comprises the steps: enabling a CNN (Convolutional Neural Network) and a self-attention mechanism self-to carry out the self-attention of the CNN; combining an action, an information selection gate and a Maxout network for use, and controlling inflow of original text information in the information coding stage so as to select important information; and meanwhile, further selecting the most important decoding information as output by using the Maxout network in the decoding stage. According to the method, the problem of repeated abstract word generation is effectively solved, and useless information can be filtered out as much as possible on the basis that important information of an original text is reserved.

Description

Technical field [0001] The invention belongs to the technical field of text information processing, and specifically relates to the design of an automatic text summarization method. Background technique [0002] At present, the automatic text summarization techniques commonly used at home and abroad can be divided into three types. According to the different methods of abstract generation, they are divided into: extractive, compressed and generative. [0003] The extraction method is simple to implement. It only extracts existing sentences from the document to form a summary, and can retain the complete sentences in the document. The generated summary is well readable and can be regarded as a combined optimization problem. In the early years, extractive methods were widely used. So far, extractive summaries have been a relatively mature solution. Among them, the Text rank ranking algorithm is widely used in the industry due to its simplicity and efficiency. The general idea is to ...

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): G06F16/34G06F17/22G06N3/04
CPCG06F16/345G06F40/12G06N3/045
Inventor 李建平顾小丰胡健李伟于腾秋孙睿男李顺利
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com