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

Triple extraction method and device

A technology of triples and information units, applied in the computer field, can solve the problems of inability to extract relationship modification attributes, insufficient information of triples, etc., and achieve the effect of enriching information.

Active Publication Date: 2020-05-19
BEIJING MININGLAMP SOFTWARE SYST CO LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Triple extraction plays a vital role in the construction of knowledge graphs, but traditional triple extraction is generally based on entity recognition and relationship classification processes. Since the modified attributes of the relationship cannot be extracted, the obtained triple information is not rich enough.

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
  • Triple extraction method and device
  • Triple extraction method and device
  • Triple extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] Such as figure 1 As shown, the embodiment of the present invention provides a triplet extraction method, including:

[0021] Step S110, perform word segmentation on the text, perform part-of-speech tagging and named entity recognition according to the word segmentation results, merge the word segments with semantic connections in the text according to the semantic merging rules to generate semantic blocks, and perform part-of-speech tagging and named entities on the semantic blocks identification;

[0022] Step S120, traversing all the information units of the text to obtain the dependency relationship between each information unit and other information units; searching for combinations of information units that can form triples based on the dependencies of information units, and generating a core from the searched information unit combinations triplet; wherein, the information unit is a semantic block or an unmerged participle; the triplet includes a subject, a predic...

Embodiment 2

[0096] Such as Figure 4 As shown, the embodiment of the present invention provides a triplet extraction device, including:

[0097] The information unit generation module 10 is used to perform word segmentation on the text, perform part-of-speech tagging and named entity recognition according to the word segmentation results, merge the word segmentations with semantic connections in the text according to the semantic merging rules to generate semantic blocks, and perform semantic block processing on the semantic blocks. Part-of-speech tagging and named entity recognition;

[0098] The core triplet building module 20 is used to traverse all information units of the text to obtain the dependency relationship between each information unit and other information units; search for information unit combinations that can form triples based on the dependency relationship of information units, and search The combination of the obtained information units generates a core triple; wherei...

Embodiment 3

[0117] An embodiment of the present invention provides a triplet extraction device, comprising: a memory, a processor, and a triplet extraction program stored on the memory and operable on the processor, the triplet extraction program When executed by the processor, the steps of the triplet extraction method described in Embodiment 1 above are implemented.

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 triple extraction method and device, and the method comprises the steps: carrying out the word segmentation, part-of-speech tagging and named entity recognition of a text, and carrying out the combination of segmented words with semantic relation according to a semantic combination rule, and generating a semantic block; obtaining a dependency relationship between each information unit in the text and other information units, and searching for the information unit combination based on the dependency relationship to generate a core triple, wherein the information unit is a semantic block or an uncombined segmented word; for any core triple, the core tripleis divided into three groups; deriving a new tripleaccording to other information units having a predetermined dependency relationship with a subject and / or an object of the core triple, and performing attribute extension on any triple of the text: searching other information units for modifying any informationunit of the triple by utilizing a dependency relationship of the information units, and taking the other information units as attributes of the information units. According to the method, the triplewith the attribute information can be extracted, so that the extracted triad information is richer.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a triplet extraction method and device. Background technique [0002] As a subset of information extraction, triplet extraction is the key to extracting predicate entities (entity recognition) that appear in the text, and performing triplets (Subject (subject), Predicate (predicate), Object) on entities with relationships. (object)) construction. [0003] Triple extraction plays a vital role in the construction of knowledge graphs, but traditional triple extraction is generally based on entity recognition and relationship classification processes. Since the modified attributes of relationships cannot be extracted, the obtained triple information is not rich enough. . Contents of the invention [0004] This paper provides a triplet extraction method and device, which can extract triplets with attribute information, so that the information of the extracted triplets is...

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): G06F40/295G06F40/30
Inventor 陈栋付骁弈
Owner BEIJING MININGLAMP SOFTWARE SYST CO LTD
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