FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971957788> ?p ?o ?g. }

• W2971957788 endingPage "862" @default.
• W2971957788 startingPage "823" @default.
• W2971957788 abstract "Since the 2001 envisioning of the Semantic Web (SW) (Scientific American 284(5) (2001) 34–43), the main research focus in SW reasoning has been on the soundness and completeness of reasoners. While these reasoners assume the veracity of input data, the reality is that the Web of data is inherently noisy. Although there has been recent work on noise-tolerant reasoning, it has focused on type inference rather than full RDFS reasoning. Even though RDFS closure generation can be seen as a Knowledge Graph (KG) completion problem, the problem setting is different – making KG embedding techniques that were designed for link prediction not suitable for RDFS reasoning. This paper documents a novel approach that extends noise-tolerance in the SW to full RDFS reasoning. Our embedding technique – that is tailored for RDFS reasoning – consists of layering RDF graphs and encoding them in the form of 3D adjacency matrices where each layer layout forms a graph word. Each input graph and its entailments are then represented as sequences of graph words, and RDFS inference can be formulated as translation of these graph words sequences, achieved through neural machine translation. Our evaluation on LUBM1 synthetic dataset shows 97% validation accuracy and 87.76% on a subset of DBpedia while demonstrating a noise-tolerance unavailable with rule-based reasoners." @default.
• W2971957788 created "2019-09-12" @default.
• W2971957788 creator A5010414972 @default.
• W2971957788 creator A5035662829 @default.
• W2971957788 date "2019-09-26" @default.
• W2971957788 modified "2023-09-24" @default.
• W2971957788 title "Deep learning for noise-tolerant RDFS reasoning1" @default.
• W2971957788 cites W102708294 @default.
• W2971957788 cites W1044785564 @default.
• W2971957788 cites W1512387364 @default.
• W2971957788 cites W1570991867 @default.
• W2971957788 cites W1824415789 @default.
• W2971957788 cites W1839979006 @default.
• W2971957788 cites W1876766592 @default.
• W2971957788 cites W1940888119 @default.
• W2971957788 cites W1977609394 @default.
• W2971957788 cites W1989009626 @default.
• W2971957788 cites W2015191210 @default.
• W2971957788 cites W202389787 @default.
• W2971957788 cites W2026417691 @default.
• W2971957788 cites W2037933327 @default.
• W2971957788 cites W2044746283 @default.
• W2971957788 cites W204615560 @default.
• W2971957788 cites W2051687086 @default.
• W2971957788 cites W2053186076 @default.
• W2971957788 cites W2073587810 @default.
• W2971957788 cites W2090634677 @default.
• W2971957788 cites W2101491706 @default.
• W2971957788 cites W2113142309 @default.
• W2971957788 cites W2116341502 @default.
• W2971957788 cites W2117431327 @default.
• W2971957788 cites W2118020555 @default.
• W2971957788 cites W2124045889 @default.
• W2971957788 cites W2131774270 @default.
• W2971957788 cites W2137862151 @default.
• W2971957788 cites W2140119009 @default.
• W2971957788 cites W2142535891 @default.
• W2971957788 cites W2165698076 @default.
• W2971957788 cites W2184957013 @default.
• W2971957788 cites W2231771044 @default.
• W2971957788 cites W2247119764 @default.
• W2971957788 cites W2250342289 @default.
• W2971957788 cites W2250539671 @default.
• W2971957788 cites W2283196293 @default.
• W2971957788 cites W2387462954 @default.
• W2971957788 cites W2491251830 @default.
• W2971957788 cites W2523679382 @default.
• W2971957788 cites W2604314403 @default.
• W2971957788 cites W2612872092 @default.
• W2971957788 cites W2621591459 @default.
• W2971957788 cites W262440584 @default.
• W2971957788 cites W2626979519 @default.
• W2971957788 cites W2737852505 @default.
• W2971957788 cites W2759136286 @default.
• W2971957788 cites W2761081518 @default.
• W2971957788 cites W2767556650 @default.
• W2971957788 cites W2962756421 @default.
• W2971957788 cites W2963224980 @default.
• W2971957788 cites W2964199361 @default.
• W2971957788 cites W3100330855 @default.
• W2971957788 cites W37178333 @default.
• W2971957788 cites W4239696231 @default.
• W2971957788 cites W68132019 @default.
• W2971957788 cites W86426707 @default.
• W2971957788 cites W2030827961 @default.
• W2971957788 doi "https://doi.org/10.3233/sw-190363" @default.
• W2971957788 hasPublicationYear "2019" @default.
• W2971957788 type Work @default.
• W2971957788 sameAs 2971957788 @default.
• W2971957788 citedByCount "19" @default.
• W2971957788 countsByYear W29719577882019 @default.
• W2971957788 countsByYear W29719577882020 @default.
• W2971957788 countsByYear W29719577882021 @default.
• W2971957788 countsByYear W29719577882022 @default.
• W2971957788 countsByYear W29719577882023 @default.
• W2971957788 crossrefType "journal-article" @default.
• W2971957788 hasAuthorship W2971957788A5010414972 @default.
• W2971957788 hasAuthorship W2971957788A5035662829 @default.
• W2971957788 hasConcept C119857082 @default.
• W2971957788 hasConcept C132525143 @default.
• W2971957788 hasConcept C147497476 @default.
• W2971957788 hasConcept C154945302 @default.
• W2971957788 hasConcept C15657843 @default.
• W2971957788 hasConcept C180356752 @default.
• W2971957788 hasConcept C199360897 @default.
• W2971957788 hasConcept C204321447 @default.
• W2971957788 hasConcept C2129575 @default.
• W2971957788 hasConcept C2776214188 @default.
• W2971957788 hasConcept C39920170 @default.
• W2971957788 hasConcept C41008148 @default.
• W2971957788 hasConcept C41009113 @default.
• W2971957788 hasConcept C41608201 @default.
• W2971957788 hasConcept C80444323 @default.
• W2971957788 hasConceptScore W2971957788C119857082 @default.
• W2971957788 hasConceptScore W2971957788C132525143 @default.
• W2971957788 hasConceptScore W2971957788C147497476 @default.
• W2971957788 hasConceptScore W2971957788C154945302 @default.
• W2971957788 hasConceptScore W2971957788C15657843 @default.

• next