Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207813134> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W3207813134 endingPage "196" @default.
- W3207813134 startingPage "186" @default.
- W3207813134 abstract "Knowledge graph (KG) embedding models suffer from the incompleteness issue of observed facts. Different from existing solutions that incorporate additional information or employ expressive and complex embedding techniques, we propose to augment KGs by iteratively mining logical rules from the observed facts and then using the rules to generate new relational triples. We incrementally train KG embeddings with the coming of new augmented triples, and leverage the embeddings to validate these new triples. To guarantee the quality of the augmented data, we filter out the noisy triples based on a propagation mechanism during the validation. The mined rules and rule groundings are human-understandable, and can make the augmentation procedure reliable. Our KG augmentation framework is applicable to any KG embedding models with no need to modify their embedding techniques. Our experiments on two popular embedding-based tasks (i.e., entity alignment and link prediction) show that the proposed framework can bring significant improvement to existing KG embedding models on most benchmark datasets." @default.
- W3207813134 created "2021-10-25" @default.
- W3207813134 creator A5000510528 @default.
- W3207813134 creator A5013878126 @default.
- W3207813134 creator A5025739250 @default.
- W3207813134 creator A5062378128 @default.
- W3207813134 creator A5078547714 @default.
- W3207813134 date "2021-01-01" @default.
- W3207813134 modified "2023-10-01" @default.
- W3207813134 title "Rule-based data augmentation for knowledge graph embedding" @default.
- W3207813134 cites W2775795276 @default.
- W3207813134 cites W3003265726 @default.
- W3207813134 cites W3012000912 @default.
- W3207813134 cites W3120491054 @default.
- W3207813134 doi "https://doi.org/10.1016/j.aiopen.2021.09.003" @default.
- W3207813134 hasPublicationYear "2021" @default.
- W3207813134 type Work @default.
- W3207813134 sameAs 3207813134 @default.
- W3207813134 citedByCount "3" @default.
- W3207813134 countsByYear W32078131342021 @default.
- W3207813134 countsByYear W32078131342022 @default.
- W3207813134 countsByYear W32078131342023 @default.
- W3207813134 crossrefType "journal-article" @default.
- W3207813134 hasAuthorship W3207813134A5000510528 @default.
- W3207813134 hasAuthorship W3207813134A5013878126 @default.
- W3207813134 hasAuthorship W3207813134A5025739250 @default.
- W3207813134 hasAuthorship W3207813134A5062378128 @default.
- W3207813134 hasAuthorship W3207813134A5078547714 @default.
- W3207813134 hasBestOaLocation W32078131341 @default.
- W3207813134 hasConcept C119857082 @default.
- W3207813134 hasConcept C124101348 @default.
- W3207813134 hasConcept C132525143 @default.
- W3207813134 hasConcept C13280743 @default.
- W3207813134 hasConcept C153083717 @default.
- W3207813134 hasConcept C154945302 @default.
- W3207813134 hasConcept C185798385 @default.
- W3207813134 hasConcept C205649164 @default.
- W3207813134 hasConcept C2987255567 @default.
- W3207813134 hasConcept C41008148 @default.
- W3207813134 hasConcept C41608201 @default.
- W3207813134 hasConcept C80444323 @default.
- W3207813134 hasConceptScore W3207813134C119857082 @default.
- W3207813134 hasConceptScore W3207813134C124101348 @default.
- W3207813134 hasConceptScore W3207813134C132525143 @default.
- W3207813134 hasConceptScore W3207813134C13280743 @default.
- W3207813134 hasConceptScore W3207813134C153083717 @default.
- W3207813134 hasConceptScore W3207813134C154945302 @default.
- W3207813134 hasConceptScore W3207813134C185798385 @default.
- W3207813134 hasConceptScore W3207813134C205649164 @default.
- W3207813134 hasConceptScore W3207813134C2987255567 @default.
- W3207813134 hasConceptScore W3207813134C41008148 @default.
- W3207813134 hasConceptScore W3207813134C41608201 @default.
- W3207813134 hasConceptScore W3207813134C80444323 @default.
- W3207813134 hasLocation W32078131341 @default.
- W3207813134 hasOpenAccess W3207813134 @default.
- W3207813134 hasPrimaryLocation W32078131341 @default.
- W3207813134 hasRelatedWork W2243512948 @default.
- W3207813134 hasRelatedWork W2883748392 @default.
- W3207813134 hasRelatedWork W2923818335 @default.
- W3207813134 hasRelatedWork W4205349486 @default.
- W3207813134 hasRelatedWork W4206547516 @default.
- W3207813134 hasRelatedWork W4226361842 @default.
- W3207813134 hasRelatedWork W4296285654 @default.
- W3207813134 hasRelatedWork W4310879833 @default.
- W3207813134 hasRelatedWork W4385279070 @default.
- W3207813134 hasRelatedWork W3129794543 @default.
- W3207813134 hasVolume "2" @default.
- W3207813134 isParatext "false" @default.
- W3207813134 isRetracted "false" @default.
- W3207813134 magId "3207813134" @default.
- W3207813134 workType "article" @default.