Multiple file summarization method based on sentence relation graph

A sentence relationship, multi-document technology, applied in instrumentation, computing, electrical digital data processing, etc., can solve the problem of not adopting effective measures, maintaining novelty, and not considering the diffusible characteristics of the relationship between sentences.

Active Publication Date: 2008-11-19
PEKING UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The above graph structure-based methods do not employ effective measures to preserve the novelty of sentences in summaries.
Meanwhile, the above graph structure-based methods do not distinguish between different types of relations between sentences, which have different contributions to the calculation of sentence importance.
Finally, the existing above-mentioned methods only simply use the content of the sentence itself to calculate the relationship between sentences, without considering the diffusible characteristics of the relationship between sentences

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
  • Multiple file summarization method based on sentence relation graph
  • Multiple file summarization method based on sentence relation graph
  • Multiple file summarization method based on sentence relation graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] Further illustrate the method of the present invention below in conjunction with embodiment and accompanying drawing:

[0073] Such as figure 1 As shown, a multi-document summarization method based on a sentence relational graph includes the following steps:

[0074] (1) Read in the documents, divide each document into sentences, and construct a sentence relationship graph for the sentence set S;

[0075] When constructing a sentence relationship graph for a sentence set S, the specific method is as follows:

[0076] 1) Construct the initial sentence relationship graph;

[0077] For any two sentences s in S i and s j The similarity value is calculated using the following cosine formula:

[0078] aff ( s i , s j ) = cos ( 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

To overcome the defect in prior art, the invention calculated the true semantic relation with diffusion character of sentence relation, and makes a difference between the sentences inside the document and within documents. This invention has well effect in practical evaluating.

Description

technical field [0001] The invention belongs to the technical field of language and word processing and information retrieval, and in particular relates to a multi-document summarization method based on a sentence relationship graph. Background technique [0002] Multi-document summarization is a core problem in the field of natural language processing, and has been widely used in applications such as text / web site (Web) content retrieval in recent years. For example, search engines such as Google and Baidu all provide news services, and form multiple news topics by collecting news information on the Internet. Brief and concise summary. [0003] The difficulty of multi-document summarization is that the information contained in different documents has a large degree of repetition and redundancy. Therefore, a good multi-document summarization method must be able to effectively fuse the effective information in different documents, that is, the generated document summarizatio...

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): G06F17/30G06F17/27
Inventor 万小军杨建武吴於茜陈晓鸥
Owner PEKING UNIV
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