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

Text summarization method and system based on deep learning combined with accumulated attention mechanism

A deep learning and attention technology, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve the problems of lack of coherence and readability of sentences, large key information, etc.

Inactive Publication Date: 2019-04-16
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generative summaries are closer to the process of human-generated summaries, but they still face problems such as the lack of coherence and readability of the generated sentences, while extractive summaries copy the original text, which will generate greater redundancy and lose key information at the same time. Bigger sex

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
  • Text summarization method and system based on deep learning combined with accumulated attention mechanism
  • Text summarization method and system based on deep learning combined with accumulated attention mechanism
  • Text summarization method and system based on deep learning combined with accumulated attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0040] In related technologies, the drawbacks of extractive summarization that have been widely studied are more prominent in long texts, especially in multiple documents. The central idea of ​​the text is usually reflected in the interrelationships between sentences, while extractive summarization generally uses word frequency, position and other information to measure the importance of keywords, and then extends to the entire sentence. This method cannot capture the text very well. Deep semantic connections between s...

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 text summarization method and system based on deep learning combined with an accumulated attention mechanism, and the method comprises the following steps: reading an original text through a coding and decoding framework to generate summary information, and positioning the key information of the current moment through the accumulated attention mechanism; copying key information from the original text through a pointer generation network; and inhibiting the repeated output through a coverage loss mechanism to obtain a final abstract of the original text. According to the method, an attention accumulation mechanism and a coverage loss mechanism are combined, so that the generated abstract easily grasps an article center, and the abstract has coherence and readability and does not have a repetition phenomenon.

Description

technical field [0001] The present invention relates to the technical field of text information mining, in particular to a text summarization method and system based on deep learning combined with a cumulative attention mechanism. Background technique [0002] In today's Internet environment, overwhelming network traffic floods our lives, and the explosive growth of representative text information makes the information overload, and the huge information makes people spend a lot of time browsing and reading. How to solve information overload and quickly extract key information from text data has become an urgent need. Text summarization is the epitome of the essence of document content, and it is an important tool to improve the efficiency of user search and reading comprehension. However, traditional summarization is manually generated, which is too costly and inefficient, so automatic text summarization technology came into being. [0003] According to Radev's definition, ...

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): G06F17/27
CPCG06F40/253G06F40/284G06F40/30
Inventor 鄂海红宋美娜胡莺夕
Owner BEIJING UNIV OF POSTS & TELECOMM
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