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

A method and system for generating abstracts applied to reading robots

A robot and summary technology, applied in the field of natural language processing research, can solve problems such as complex semantic information that is not used in the article, and achieve the effect of clear thinking structure, obvious effect, and strong scalability

Active Publication Date: 2022-05-27
SHANXI UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Although a lot of research has been done and great progress has been made, the above work either directly splices external knowledge as word vector features into the text word vector, or extracts the entity information in the article to guide the summary generation, and The complex semantic information contained in the article itself is not used

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
  • A method and system for generating abstracts applied to reading robots
  • A method and system for generating abstracts applied to reading robots
  • A method and system for generating abstracts applied to reading robots

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0086] The present invention will now be further described in detail with reference to the accompanying drawings. The accompanying drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the structures related to the present invention.

[0087] Embodiments of the present invention provide a system for generating abstracts for a reading robot, such as figure 1 As shown, the system flow chart of the present invention includes six parts: a candidate abstract extraction unit, a frame selection unit, a frame encoding unit, an article encoding unit, a frame and article interaction unit, and a decoding unit.

[0088] The candidate abstract extraction unit is used to extract the most similar article D of the current article D in the training set can , Article D can Abstract as candidate abstract S can , which guides abstract generation. After comprehensively considering the extract...

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 method and system for generating an abstract applied to a reading robot; it includes the following steps: 1. A candidate abstract extraction unit extracts the abstract of the article most similar to the current article in the training set as a candidate abstract; 2. A frame selection unit , using two measurement methods of frame relationship and frame similarity to screen out important frames in the article; 3. Frame coding unit, to obtain the vector representation of the frame; 4. Article coding unit, to obtain the vector representation of the article; 5. Interaction between frames and articles Unit, calculates the interaction between the framework and the article, and obtains the final article representation; six, the decoding unit, generates a summary according to the obtained article representation. The present invention introduces the frame semantic information for the first time, integrates it into the abstract generation model, calculates the interaction between the frame and the article, and effectively improves the abstract generation result. The thinking structure of the method of the invention is clear, the effect is obvious, and the expandability is strong.

Description

technical field [0001] The invention belongs to the research field of natural language processing, and in particular relates to a method and system for generating abstracts applied to a reading robot. Background technique [0002] Abstracts are simple and coherent short texts that fully and accurately reflect the main content of a text. Automatic summarization is the use of computer to automatically extract abstracts from original texts, which aims to provide users with a short representation of texts and facilitate users to obtain textual information quickly and efficiently. The technology is widely used in various fields, such as military, public safety, enterprise, publishing, medical and so on. At the same time, in the face of the explosive growth of data, text summarization has gradually become a hot spot in natural language processing (NLP). [0003] The early text summarization technology was mainly based on some feature-based methods. Knight, K.; and Marcu, D. 200...

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 Patents(China)
IPC IPC(8): G06F40/194G06F16/34G06F40/289G06F40/30G06N3/04
CPCG06F40/194G06F16/345G06F40/30G06F40/289G06N3/044G06N3/045
Inventor 关勇李茹郭少茹谭红叶张虎
Owner SHANXI 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

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