Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971369872> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2971369872 abstract "Knowledge graphs are useful for many artificial intelligence tasks but often have missing data. Hence, a method for completing knowledge graphs is required. Existing approaches include embedding models, the Path Ranking Algorithm, and rule evaluation models. However, these approaches have limitations. For example, all the information is mixed and difficult to interpret in embedding models, and traditional rule evaluation models are basically slow. In this paper, we provide an integrated view of various approaches and combine them to compensate for their limitations. We first unify state-of-the-art embedding models, such as ComplEx and TorusE, reinterpreting them as a variant of translation-based models. Then, we show that these models utilize paths for link prediction and propose a method for evaluating rules based on this idea. Finally, we combine an embedding model and observed feature models to predict missing triples. This is possible because all of these models utilize paths. We also conduct experiments, including link prediction tasks, with standard datasets to evaluate our method and framework. The experiments show that our method can evaluate rules faster than traditional methods and that our framework outperforms state-of-the-art models in terms of link prediction." @default.
- W2971369872 created "2019-09-12" @default.
- W2971369872 creator A5072839216 @default.
- W2971369872 creator A5081854769 @default.
- W2971369872 date "2019-09-09" @default.
- W2971369872 modified "2023-09-25" @default.
- W2971369872 title "Combination of Unified Embedding Model and Observed Features for Knowledge Graph Completion" @default.
- W2971369872 cites W102708294 @default.
- W2971369872 cites W1533230146 @default.
- W2971369872 cites W1756422141 @default.
- W2971369872 cites W1894439495 @default.
- W2971369872 cites W2022166150 @default.
- W2971369872 cites W2026810221 @default.
- W2971369872 cites W2029249040 @default.
- W2971369872 cites W2030432398 @default.
- W2971369872 cites W205829674 @default.
- W2971369872 cites W2081580037 @default.
- W2971369872 cites W2094728533 @default.
- W2971369872 cites W2107306718 @default.
- W2971369872 cites W2127795553 @default.
- W2971369872 cites W2151502664 @default.
- W2971369872 cites W2184957013 @default.
- W2971369872 cites W2250184916 @default.
- W2971369872 cites W2250342289 @default.
- W2971369872 cites W2283196293 @default.
- W2971369872 cites W2340448811 @default.
- W2971369872 cites W2563063592 @default.
- W2971369872 cites W2808652502 @default.
- W2971369872 cites W2962686142 @default.
- W2971369872 cites W2963203544 @default.
- W2971369872 cites W2963359213 @default.
- W2971369872 cites W2963432357 @default.
- W2971369872 cites W2963450615 @default.
- W2971369872 cites W2964015378 @default.
- W2971369872 cites W2964116313 @default.
- W2971369872 doi "https://doi.org/10.48550/arxiv.1909.03821" @default.
- W2971369872 hasPublicationYear "2019" @default.
- W2971369872 type Work @default.
- W2971369872 sameAs 2971369872 @default.
- W2971369872 citedByCount "0" @default.
- W2971369872 crossrefType "posted-content" @default.
- W2971369872 hasAuthorship W2971369872A5072839216 @default.
- W2971369872 hasAuthorship W2971369872A5081854769 @default.
- W2971369872 hasBestOaLocation W29713698721 @default.
- W2971369872 hasConcept C119857082 @default.
- W2971369872 hasConcept C124101348 @default.
- W2971369872 hasConcept C132525143 @default.
- W2971369872 hasConcept C154945302 @default.
- W2971369872 hasConcept C189430467 @default.
- W2971369872 hasConcept C2778753846 @default.
- W2971369872 hasConcept C2987255567 @default.
- W2971369872 hasConcept C31258907 @default.
- W2971369872 hasConcept C41008148 @default.
- W2971369872 hasConcept C41608201 @default.
- W2971369872 hasConcept C80444323 @default.
- W2971369872 hasConceptScore W2971369872C119857082 @default.
- W2971369872 hasConceptScore W2971369872C124101348 @default.
- W2971369872 hasConceptScore W2971369872C132525143 @default.
- W2971369872 hasConceptScore W2971369872C154945302 @default.
- W2971369872 hasConceptScore W2971369872C189430467 @default.
- W2971369872 hasConceptScore W2971369872C2778753846 @default.
- W2971369872 hasConceptScore W2971369872C2987255567 @default.
- W2971369872 hasConceptScore W2971369872C31258907 @default.
- W2971369872 hasConceptScore W2971369872C41008148 @default.
- W2971369872 hasConceptScore W2971369872C41608201 @default.
- W2971369872 hasConceptScore W2971369872C80444323 @default.
- W2971369872 hasLocation W29713698721 @default.
- W2971369872 hasOpenAccess W2971369872 @default.
- W2971369872 hasPrimaryLocation W29713698721 @default.
- W2971369872 hasRelatedWork W2784239688 @default.
- W2971369872 hasRelatedWork W2923818335 @default.
- W2971369872 hasRelatedWork W2979603757 @default.
- W2971369872 hasRelatedWork W3103545790 @default.
- W2971369872 hasRelatedWork W4206939502 @default.
- W2971369872 hasRelatedWork W4226361842 @default.
- W2971369872 hasRelatedWork W4310879833 @default.
- W2971369872 hasRelatedWork W4312327654 @default.
- W2971369872 hasRelatedWork W4312937211 @default.
- W2971369872 hasRelatedWork W4323362462 @default.
- W2971369872 isParatext "false" @default.
- W2971369872 isRetracted "false" @default.
- W2971369872 magId "2971369872" @default.
- W2971369872 workType "article" @default.