Example of knowledge graph.

<div><p>Background</p><p>The field of information extraction (IE) is currently exploring more versatile and efficient methods for minimization of reliance on extensive annotated datasets and integration of knowledge across tasks and domains.</p><p>Objective</p&...

Full description

Saved in:
Bibliographic Details
Main Author: Bei Li (90587) (author)
Other Authors: Changbiao Li (14356569) (author), Jianwei Sun (263070) (author), Xu Zeng (402015) (author), Xiaofan Chen (140368) (author), Jing Zheng (65946) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852019886284341248
author Bei Li (90587)
author2 Changbiao Li (14356569)
Jianwei Sun (263070)
Xu Zeng (402015)
Xiaofan Chen (140368)
Jing Zheng (65946)
author2_role author
author
author
author
author
author_facet Bei Li (90587)
Changbiao Li (14356569)
Jianwei Sun (263070)
Xu Zeng (402015)
Xiaofan Chen (140368)
Jing Zheng (65946)
author_role author
dc.creator.none.fl_str_mv Bei Li (90587)
Changbiao Li (14356569)
Jianwei Sun (263070)
Xu Zeng (402015)
Xiaofan Chen (140368)
Jing Zheng (65946)
dc.date.none.fl_str_mv 2025-05-29T17:48:18Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0325082.g008
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Example_of_knowledge_graph_/29188515
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Marine Biology
Cancer
Science Policy
Infectious Diseases
Plant Biology
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
chinese medical expertise
achieving commendable results
extensive annotated datasets
data stored within
knowledge across tasks
conducting knowledge mining
jointly extracted using
minimal annotated data
generative extraction paradigm
graph &# 8217
xlink "> incorporating
pretrained language model
medical knowledge graph
advancing information extraction
annotated data
xlink ">
knowledge graph
information extraction
graph databases
knowledge integration
web scraping
tuning strategies
thereby contributing
storage techniques
small amount
optimized using
enhanced representation
efficient methods
currently exploring
course management
cost savings
construction process
construction model
approach addresses
dc.title.none.fl_str_mv Example of knowledge graph.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>Background</p><p>The field of information extraction (IE) is currently exploring more versatile and efficient methods for minimization of reliance on extensive annotated datasets and integration of knowledge across tasks and domains.</p><p>Objective</p><p>We aim to evaluate and refine the application of the universal IE (UIE) technology in the field of Chinese medical expertise in terms of processing accuracy and efficiency.</p><p>Methods</p><p>Our model integrates ontology modeling, web scraping, UIE, fine-tuning strategies, and graph databases, thereby covering knowledge modeling, extraction, and storage techniques. The Enhanced Representation through Knowledge Integration-UIE (ERNIE-UIE) model is fine-tuned and optimized using a small amount of annotated data. A medical knowledge graph is then constructed, followed by validating the graph and conducting knowledge mining on the data stored within it.</p><p>Results</p><p>Incorporating the characteristics of whole-course management, we implemented a comprehensive medical knowledge graph–construction model and methodology. Entities and relationships were jointly extracted using the pretrained language model, resulting in 8,525 entity data points and 9,522 triple data points. The accuracy of the knowledge graph was verified using graph algorithms.</p><p>Conclusion</p><p>We optimized the construction process of a Chinese medical knowledge graph with minimal annotated data by utilizing a generative extraction paradigm, validating the graph’s efficacy and achieving commendable results. This approach addresses the challenge of insufficient annotated training corpora in low-resource knowledge graph construction, thereby contributing to cost savings in the development of knowledge graphs.</p></div>
eu_rights_str_mv openAccess
id Manara_ca2fb5f7dd1d18211f627e3ced7abdfd
identifier_str_mv 10.1371/journal.pone.0325082.g008
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29188515
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Example of knowledge graph.Bei Li (90587)Changbiao Li (14356569)Jianwei Sun (263070)Xu Zeng (402015)Xiaofan Chen (140368)Jing Zheng (65946)Marine BiologyCancerScience PolicyInfectious DiseasesPlant BiologyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedchinese medical expertiseachieving commendable resultsextensive annotated datasetsdata stored withinknowledge across tasksconducting knowledge miningjointly extracted usingminimal annotated datagenerative extraction paradigmgraph &# 8217xlink "> incorporatingpretrained language modelmedical knowledge graphadvancing information extractionannotated dataxlink ">knowledge graphinformation extractiongraph databasesknowledge integrationweb scrapingtuning strategiesthereby contributingstorage techniquessmall amountoptimized usingenhanced representationefficient methodscurrently exploringcourse managementcost savingsconstruction processconstruction modelapproach addresses<div><p>Background</p><p>The field of information extraction (IE) is currently exploring more versatile and efficient methods for minimization of reliance on extensive annotated datasets and integration of knowledge across tasks and domains.</p><p>Objective</p><p>We aim to evaluate and refine the application of the universal IE (UIE) technology in the field of Chinese medical expertise in terms of processing accuracy and efficiency.</p><p>Methods</p><p>Our model integrates ontology modeling, web scraping, UIE, fine-tuning strategies, and graph databases, thereby covering knowledge modeling, extraction, and storage techniques. The Enhanced Representation through Knowledge Integration-UIE (ERNIE-UIE) model is fine-tuned and optimized using a small amount of annotated data. A medical knowledge graph is then constructed, followed by validating the graph and conducting knowledge mining on the data stored within it.</p><p>Results</p><p>Incorporating the characteristics of whole-course management, we implemented a comprehensive medical knowledge graph–construction model and methodology. Entities and relationships were jointly extracted using the pretrained language model, resulting in 8,525 entity data points and 9,522 triple data points. The accuracy of the knowledge graph was verified using graph algorithms.</p><p>Conclusion</p><p>We optimized the construction process of a Chinese medical knowledge graph with minimal annotated data by utilizing a generative extraction paradigm, validating the graph’s efficacy and achieving commendable results. This approach addresses the challenge of insufficient annotated training corpora in low-resource knowledge graph construction, thereby contributing to cost savings in the development of knowledge graphs.</p></div>2025-05-29T17:48:18ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0325082.g008https://figshare.com/articles/figure/Example_of_knowledge_graph_/29188515CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/291885152025-05-29T17:48:18Z
spellingShingle Example of knowledge graph.
Bei Li (90587)
Marine Biology
Cancer
Science Policy
Infectious Diseases
Plant Biology
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
chinese medical expertise
achieving commendable results
extensive annotated datasets
data stored within
knowledge across tasks
conducting knowledge mining
jointly extracted using
minimal annotated data
generative extraction paradigm
graph &# 8217
xlink "> incorporating
pretrained language model
medical knowledge graph
advancing information extraction
annotated data
xlink ">
knowledge graph
information extraction
graph databases
knowledge integration
web scraping
tuning strategies
thereby contributing
storage techniques
small amount
optimized using
enhanced representation
efficient methods
currently exploring
course management
cost savings
construction process
construction model
approach addresses
status_str publishedVersion
title Example of knowledge graph.
title_full Example of knowledge graph.
title_fullStr Example of knowledge graph.
title_full_unstemmed Example of knowledge graph.
title_short Example of knowledge graph.
title_sort Example of knowledge graph.
topic Marine Biology
Cancer
Science Policy
Infectious Diseases
Plant Biology
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
chinese medical expertise
achieving commendable results
extensive annotated datasets
data stored within
knowledge across tasks
conducting knowledge mining
jointly extracted using
minimal annotated data
generative extraction paradigm
graph &# 8217
xlink "> incorporating
pretrained language model
medical knowledge graph
advancing information extraction
annotated data
xlink ">
knowledge graph
information extraction
graph databases
knowledge integration
web scraping
tuning strategies
thereby contributing
storage techniques
small amount
optimized using
enhanced representation
efficient methods
currently exploring
course management
cost savings
construction process
construction model
approach addresses