Completing Scientific Facts in Knowledge Graphs of Research Concepts

In the last few years, we have witnessed the emergence of several knowledge graphs that explicitly describe research knowledge with the aim of enabling intelligent systems for supporting and accelerating the scientific process. These resources typically characterize a set of entities in this space (...

Descripción completa

Detalles Bibliográficos
Autores: Borrego Díaz, Agustín, Dessì, Danilo, Hernández Salmerón, Inmaculada Concepción, Osborne, Francesco, Reforgiato Recupero, Diego, Ruiz Cortés, David, Buscaldi, Davide, Motta, Enrico
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/144473
Acceso en línea:https://hdl.handle.net/11441/144473
https://doi.org/10.1109/ACCESS.2022.3220241
Access Level:acceso abierto
Palabra clave:Knowledge graphs
science of science
knowledge graph completion
triple classification
machine learning
semantic web
id ES_0affb330d6e37f43e8bfdf251dfad737
oai_identifier_str oai:idus.us.es:11441/144473
network_acronym_str ES
network_name_str España
repository_id_str
spelling Completing Scientific Facts in Knowledge Graphs of Research ConceptsBorrego Díaz, AgustínDessì, DaniloHernández Salmerón, Inmaculada ConcepciónOsborne, FrancescoReforgiato Recupero, DiegoRuiz Cortés, DavidBuscaldi, DavideMotta, EnricoKnowledge graphsscience of scienceknowledge graph completiontriple classificationmachine learningsemantic webIn the last few years, we have witnessed the emergence of several knowledge graphs that explicitly describe research knowledge with the aim of enabling intelligent systems for supporting and accelerating the scientific process. These resources typically characterize a set of entities in this space (e.g., tasks, methods, evaluation techniques, proteins, chemicals), their relations, and the relevant actors (e.g., researchers, organizations) and documents (e.g., articles, books). However, they are usually very partial representations of the actual research knowledge and may miss several relevant facts. In this paper, we introduce SciCheck, a new triple classification approach for completing scientific statements in knowledge graphs. SciCheck was evaluated against other state-of-the-art approaches on seven benchmarks, yielding excellent results. Finally, we provide a real-world use case and applied SciCheck to the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically-generated open knowledge graph including 1.2M statements extracted from the 333K most cited articles in the field of Artificial Intelligence, and generated a new version of this knowledge graph with 300K additional triplesMinisterio de Ciencia, Innovación y Universidades PID2019-105471RB-I00Junta de Andalucía P18-RT-1060Junta de Andalucía US-1380565IEEE XploreLenguajes y Sistemas InformáticosMinisterio de Ciencia, Innovación y Universidades (MICINN). EspañaJunta de Andalucía2022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/144473https://doi.org/10.1109/ACCESS.2022.3220241reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésIEEE Access, 10, 125867-125880.PID2019-105471RB-I00P18-RT-1060US-1380565https://ieeexplore.ieee.org/document/9940925info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1444732026-06-17T12:51:07Z
dc.title.none.fl_str_mv Completing Scientific Facts in Knowledge Graphs of Research Concepts
title Completing Scientific Facts in Knowledge Graphs of Research Concepts
spellingShingle Completing Scientific Facts in Knowledge Graphs of Research Concepts
Borrego Díaz, Agustín
Knowledge graphs
science of science
knowledge graph completion
triple classification
machine learning
semantic web
title_short Completing Scientific Facts in Knowledge Graphs of Research Concepts
title_full Completing Scientific Facts in Knowledge Graphs of Research Concepts
title_fullStr Completing Scientific Facts in Knowledge Graphs of Research Concepts
title_full_unstemmed Completing Scientific Facts in Knowledge Graphs of Research Concepts
title_sort Completing Scientific Facts in Knowledge Graphs of Research Concepts
dc.creator.none.fl_str_mv Borrego Díaz, Agustín
Dessì, Danilo
Hernández Salmerón, Inmaculada Concepción
Osborne, Francesco
Reforgiato Recupero, Diego
Ruiz Cortés, David
Buscaldi, Davide
Motta, Enrico
author Borrego Díaz, Agustín
author_facet Borrego Díaz, Agustín
Dessì, Danilo
Hernández Salmerón, Inmaculada Concepción
Osborne, Francesco
Reforgiato Recupero, Diego
Ruiz Cortés, David
Buscaldi, Davide
Motta, Enrico
author_role author
author2 Dessì, Danilo
Hernández Salmerón, Inmaculada Concepción
Osborne, Francesco
Reforgiato Recupero, Diego
Ruiz Cortés, David
Buscaldi, Davide
Motta, Enrico
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
Ministerio de Ciencia, Innovación y Universidades (MICINN). España
Junta de Andalucía
dc.subject.none.fl_str_mv Knowledge graphs
science of science
knowledge graph completion
triple classification
machine learning
semantic web
topic Knowledge graphs
science of science
knowledge graph completion
triple classification
machine learning
semantic web
description In the last few years, we have witnessed the emergence of several knowledge graphs that explicitly describe research knowledge with the aim of enabling intelligent systems for supporting and accelerating the scientific process. These resources typically characterize a set of entities in this space (e.g., tasks, methods, evaluation techniques, proteins, chemicals), their relations, and the relevant actors (e.g., researchers, organizations) and documents (e.g., articles, books). However, they are usually very partial representations of the actual research knowledge and may miss several relevant facts. In this paper, we introduce SciCheck, a new triple classification approach for completing scientific statements in knowledge graphs. SciCheck was evaluated against other state-of-the-art approaches on seven benchmarks, yielding excellent results. Finally, we provide a real-world use case and applied SciCheck to the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically-generated open knowledge graph including 1.2M statements extracted from the 333K most cited articles in the field of Artificial Intelligence, and generated a new version of this knowledge graph with 300K additional triples
publishDate 2022
dc.date.none.fl_str_mv 2022
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/144473
https://doi.org/10.1109/ACCESS.2022.3220241
url https://hdl.handle.net/11441/144473
https://doi.org/10.1109/ACCESS.2022.3220241
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IEEE Access, 10, 125867-125880.
PID2019-105471RB-I00
P18-RT-1060
US-1380565
https://ieeexplore.ieee.org/document/9940925
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv IEEE Xplore
publisher.none.fl_str_mv IEEE Xplore
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403196161523712
score 15,301603

Similares en LA Referencia