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

Method and device for generating multi-document summary

A multi-document and abstract technology, applied in the fields of instrumentation, computing, electrical digital data processing, etc., can solve the problem of low readability of multi-document abstracts, and achieve the effect of improving readability

Inactive Publication Date: 2010-06-16
PEKING UNIV +2
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, embodiments of the present invention provide a method and device for generating multi-document summaries to solve the problem of low readability of multi-document summaries generated in the prior art

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
  • Method and device for generating multi-document summary
  • Method and device for generating multi-document summary
  • Method and device for generating multi-document summary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0076] Embodiment 2: In the embodiment of the present invention, when two abstract sentences a and b belong to the same document, the method for determining the order of the two abstract sentences includes:

[0077] According to the positions of the two summary sentences in the document, determine the sequence of the two summary sentences, including:

[0078]

[0079] In the above formula, pos(x) indicates the position of the summary sentence x in the document, for example, the summary sentence x is the first clause in the document, λ p determined according to the order of position The corresponding weights, and λ p is a real number greater than 0, such as λ p is 4 etc., when λp When it is 1, the order of the two summary sentences is a sign function of the position difference of the two summary sentences in the document. sgn(x) is a sign function.

[0080] Implementation 3: When two abstract sentences belong to different documents, for example, abstract sentences a and...

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 a device for generating a multi-document summary, which are used for solving the problem of bad readability of the multi-document summary generated by the prior art. The method comprises the steps of: selecting a plurality of summary sentences from a plurality of documents; and sequencing the summary sentences according to at least one set sequencing rule to generate the multi-document summary, wherein each sequencing rule is set according to date information in the summary sentences, position information of the summary sentences positioned in the documents or the interdependency between the summary sentences and summary subject contents. The technical scheme disclosed by the invention gives full consideration to the continuity among the summary sentences and the interdependency between the summary sentences and the subject contents, thereby effectively improving the readability of the generated multi-document summary.

Description

technical field [0001] The invention relates to the technical field of language and word processing, in particular to a method and device for generating multi-document summaries. Background technique [0002] Multi-document summarization can provide a compressed text description for a document set containing multiple documents, so as to solve the problem of information overload in the document set, and facilitate users to quickly understand the content of the document set. At present, there are also some methods for generating multi-document summaries, but because each sentence in multi-document summaries may come from different documents, and the writing style of each document is different, the time of publication is different, and the background knowledge relied on may also be different , Therefore, when these sentences are sorted to form an abstract, some words often have unclear references and incoherent contexts. Such a multi-document summary may not help readers quick...

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): G06F17/30G06F17/21
Inventor 贾候萍万小军黄小江杨建武肖建国
Owner PEKING 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