A Method for Automatic Abstract Generation Based on Conceptual Semantic Primitives

An automatic generation and semantic technology, applied in the field of natural language text intelligent analysis, can solve the problems of sparse data, the weight value cannot well reflect the deep semantic content of the document, etc., and achieve the effect of good user experience.

Active Publication Date: 2018-08-07
INST OF ACOUSTICS CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that the calculation of sentence weight value based on word frequency cannot well reflect the deep semantic content of the document described in the background technology, and at the same time improve the topic analysis method with words as the statistical processing unit applied to a single document and the data is sparse questions, and then form the abstract content of a single document

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 for Automatic Abstract Generation Based on Conceptual Semantic Primitives
  • A Method for Automatic Abstract Generation Based on Conceptual Semantic Primitives
  • A Method for Automatic Abstract Generation Based on Conceptual Semantic Primitives

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0136] In this embodiment, a news release is selected for abstract processing. The press release comes from the Internet, and the title is "Obama Putin and Hollande will have two dinners without meeting in France" (the specific link is http: / / news.sina.com.cn / w / 2014-06-03 / 102030282941.shtml ).

[0137] First of all, it is necessary to extract the text content in the press release, and filter out other advertising links, associated recommendation links, and picture and video link information.

[0138] Secondly, the text information will be segmented according to paragraphs and sentences. An example of this embodiment is given below.

[0139]

[0140] Here, the content of the obtained document is organized, divided and labeled according to sentences and paragraphs. 1~10 on the far left is the number of marked sentences. The document of this embodiment has 10 sentences in total. The numbers from 0 to 9 in the second column on the left are serial numbers uniformly assi...

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 present invention relates to a method for automatically generating abstracts based on conceptual semantic primitives. Semantic Gravity Selects abstract sentences that represent the content of the document to form a method for automatically generating document abstracts. The invention utilizes a latent Dirichlet allocation (LDA) model to model a document topic, realizes topic generation processing, and selects abstract sentences according to topic importance. In the calculation process, conceptual hierarchical network symbols are introduced, and the semantic hierarchical relationship is used to realize the merging of semantic information, so as to improve the data sparse problem caused by using words as semantic calculation units.

Description

technical field [0001] The invention relates to the field of intelligent analysis of natural language texts, in particular to an abstract automatic generation method based on conceptual semantic primitives. Background technique [0002] With the rapid development of information technology, the Internet has entered people's daily life. The bottleneck of information transmission has been broken, and people can easily access massive amounts of information content. How to quickly understand the content of information has become the current development direction of intelligent information processing and a hot spot in technical research. Especially with the rapid expansion of document information on the Internet, facing a large amount of document information, users urgently need tools that can effectively process these document information. Automatic text summarization, based on natural language processing technology, is an intelligent text processing application technology that...

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): G06F17/27
Inventor 张全袁毅韦向峰丛培民杜义华池毓焕
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap