Matches in SemOpenAlex for { <https://semopenalex.org/work/W4228996479> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4228996479 abstract "Graph embedding methods have emerged as effective solutions for knowledge graph completion. However, such methods are typically tested on benchmark datasets such as Freebase, but show limited performance when applied on sparse knowledge graphs with orders of magnitude lower density. To compensate for the lack of structure in a sparse graph, low dimensional representations of textual information such as word2vec or BERT embeddings have been used. This paper proposes a BERT-based method (BERT-ConvE), to exploit transfer learning of BERT in combination with a convolutional network model ConvE. Comparing to existing text-aware approaches, we effectively make use of the context dependency of BERT embeddings through optimizing the features extraction strategies. Experiments on ConceptNet show that the proposed method outperforms strong baselines by 50% on knowledge graph completion tasks. The proposed method is suitable for sparse graphs as also demonstrated by empirical studies on ATOMIC and sparsified-FB15k-237 datasets. Its effectiveness and simplicity make it appealing for industrial applications." @default.
- W4228996479 created "2022-05-08" @default.
- W4228996479 creator A5013977126 @default.
- W4228996479 creator A5014398832 @default.
- W4228996479 creator A5072129309 @default.
- W4228996479 creator A5072364762 @default.
- W4228996479 date "2022-04-25" @default.
- W4228996479 modified "2023-10-17" @default.
- W4228996479 title "Effective use of BERT in graph embeddings for sparse knowledge graph completion" @default.
- W4228996479 cites W2250184916 @default.
- W4228996479 cites W2509019445 @default.
- W4228996479 cites W2612872092 @default.
- W4228996479 cites W2728059831 @default.
- W4228996479 cites W2757431232 @default.
- W4228996479 cites W2897586972 @default.
- W4228996479 cites W2962739339 @default.
- W4228996479 cites W2970641574 @default.
- W4228996479 cites W2998374885 @default.
- W4228996479 cites W3173771700 @default.
- W4228996479 cites W3202794254 @default.
- W4228996479 doi "https://doi.org/10.1145/3477314.3507031" @default.
- W4228996479 hasPublicationYear "2022" @default.
- W4228996479 type Work @default.
- W4228996479 citedByCount "2" @default.
- W4228996479 countsByYear W42289964792023 @default.
- W4228996479 crossrefType "proceedings-article" @default.
- W4228996479 hasAuthorship W4228996479A5013977126 @default.
- W4228996479 hasAuthorship W4228996479A5014398832 @default.
- W4228996479 hasAuthorship W4228996479A5072129309 @default.
- W4228996479 hasAuthorship W4228996479A5072364762 @default.
- W4228996479 hasConcept C102192266 @default.
- W4228996479 hasConcept C119857082 @default.
- W4228996479 hasConcept C121332964 @default.
- W4228996479 hasConcept C13251829 @default.
- W4228996479 hasConcept C132525143 @default.
- W4228996479 hasConcept C154945302 @default.
- W4228996479 hasConcept C163716315 @default.
- W4228996479 hasConcept C165696696 @default.
- W4228996479 hasConcept C19768560 @default.
- W4228996479 hasConcept C203776342 @default.
- W4228996479 hasConcept C2776461190 @default.
- W4228996479 hasConcept C2987255567 @default.
- W4228996479 hasConcept C38652104 @default.
- W4228996479 hasConcept C41008148 @default.
- W4228996479 hasConcept C41608201 @default.
- W4228996479 hasConcept C56372850 @default.
- W4228996479 hasConcept C62520636 @default.
- W4228996479 hasConcept C80444323 @default.
- W4228996479 hasConceptScore W4228996479C102192266 @default.
- W4228996479 hasConceptScore W4228996479C119857082 @default.
- W4228996479 hasConceptScore W4228996479C121332964 @default.
- W4228996479 hasConceptScore W4228996479C13251829 @default.
- W4228996479 hasConceptScore W4228996479C132525143 @default.
- W4228996479 hasConceptScore W4228996479C154945302 @default.
- W4228996479 hasConceptScore W4228996479C163716315 @default.
- W4228996479 hasConceptScore W4228996479C165696696 @default.
- W4228996479 hasConceptScore W4228996479C19768560 @default.
- W4228996479 hasConceptScore W4228996479C203776342 @default.
- W4228996479 hasConceptScore W4228996479C2776461190 @default.
- W4228996479 hasConceptScore W4228996479C2987255567 @default.
- W4228996479 hasConceptScore W4228996479C38652104 @default.
- W4228996479 hasConceptScore W4228996479C41008148 @default.
- W4228996479 hasConceptScore W4228996479C41608201 @default.
- W4228996479 hasConceptScore W4228996479C56372850 @default.
- W4228996479 hasConceptScore W4228996479C62520636 @default.
- W4228996479 hasConceptScore W4228996479C80444323 @default.
- W4228996479 hasLocation W42289964791 @default.
- W4228996479 hasLocation W42289964792 @default.
- W4228996479 hasOpenAccess W4228996479 @default.
- W4228996479 hasPrimaryLocation W42289964791 @default.
- W4228996479 hasRelatedWork W1566229417 @default.
- W4228996479 hasRelatedWork W1893178273 @default.
- W4228996479 hasRelatedWork W2483318309 @default.
- W4228996479 hasRelatedWork W2539871928 @default.
- W4228996479 hasRelatedWork W2542063421 @default.
- W4228996479 hasRelatedWork W2951138411 @default.
- W4228996479 hasRelatedWork W3138826529 @default.
- W4228996479 hasRelatedWork W4299546378 @default.
- W4228996479 hasRelatedWork W4316252382 @default.
- W4228996479 hasRelatedWork W4320554512 @default.
- W4228996479 isParatext "false" @default.
- W4228996479 isRetracted "false" @default.
- W4228996479 workType "article" @default.