Matches in SemOpenAlex for { <https://semopenalex.org/work/W2551361256> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2551361256 abstract "Many recent works have demonstrated the benefits of knowledge graph embeddings in completing monolingual knowledge graphs. Inasmuch as related knowledge bases are built in several different languages, achieving cross-lingual knowledge alignment will help people in constructing a coherent knowledge base, and assist machines in dealing with different expressions of entity relationships across diverse human languages. Unfortunately, achieving this highly desirable cross-lingual alignment by human labor is very costly and error-prone. Thus, we propose MTransE, a translation-based model for multilingual knowledge graph embeddings, to provide a simple and automated solution. By encoding entities and relations of each language in a separated embedding space, MTransE provides transitions for each embedding vector to its cross-lingual counterparts in other spaces, while preserving the functionalities of monolingual embeddings. We deploy three different techniques to represent cross-lingual transitions, namely axis calibration, translation vectors, and linear transformations, and derive five variants for MTransE using different loss functions. Our models can be trained on partially aligned graphs, where just a small portion of triples are aligned with their cross-lingual counterparts. The experiments on cross-lingual entity matching and triple-wise alignment verification show promising results, with some variants consistently outperforming others on different tasks. We also explore how MTransE preserves the key properties of its monolingual counterpart." @default.
- W2551361256 created "2016-11-30" @default.
- W2551361256 creator A5024788962 @default.
- W2551361256 creator A5040295235 @default.
- W2551361256 creator A5058756889 @default.
- W2551361256 creator A5084932479 @default.
- W2551361256 date "2017-08-01" @default.
- W2551361256 modified "2023-10-10" @default.
- W2551361256 title "Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment" @default.
- W2551361256 doi "https://doi.org/10.24963/ijcai.2017/209" @default.
- W2551361256 hasPublicationYear "2017" @default.
- W2551361256 type Work @default.
- W2551361256 sameAs 2551361256 @default.
- W2551361256 citedByCount "278" @default.
- W2551361256 countsByYear W25513612562017 @default.
- W2551361256 countsByYear W25513612562018 @default.
- W2551361256 countsByYear W25513612562019 @default.
- W2551361256 countsByYear W25513612562020 @default.
- W2551361256 countsByYear W25513612562021 @default.
- W2551361256 countsByYear W25513612562022 @default.
- W2551361256 countsByYear W25513612562023 @default.
- W2551361256 crossrefType "proceedings-article" @default.
- W2551361256 hasAuthorship W2551361256A5024788962 @default.
- W2551361256 hasAuthorship W2551361256A5040295235 @default.
- W2551361256 hasAuthorship W2551361256A5058756889 @default.
- W2551361256 hasAuthorship W2551361256A5084932479 @default.
- W2551361256 hasBestOaLocation W25513612561 @default.
- W2551361256 hasConcept C104317684 @default.
- W2551361256 hasConcept C105580179 @default.
- W2551361256 hasConcept C105795698 @default.
- W2551361256 hasConcept C132525143 @default.
- W2551361256 hasConcept C13336665 @default.
- W2551361256 hasConcept C149364088 @default.
- W2551361256 hasConcept C154945302 @default.
- W2551361256 hasConcept C165064840 @default.
- W2551361256 hasConcept C185592680 @default.
- W2551361256 hasConcept C204321447 @default.
- W2551361256 hasConcept C2524010 @default.
- W2551361256 hasConcept C2987255567 @default.
- W2551361256 hasConcept C33923547 @default.
- W2551361256 hasConcept C41008148 @default.
- W2551361256 hasConcept C41608201 @default.
- W2551361256 hasConcept C4554734 @default.
- W2551361256 hasConcept C55493867 @default.
- W2551361256 hasConcept C80444323 @default.
- W2551361256 hasConcept C96711827 @default.
- W2551361256 hasConceptScore W2551361256C104317684 @default.
- W2551361256 hasConceptScore W2551361256C105580179 @default.
- W2551361256 hasConceptScore W2551361256C105795698 @default.
- W2551361256 hasConceptScore W2551361256C132525143 @default.
- W2551361256 hasConceptScore W2551361256C13336665 @default.
- W2551361256 hasConceptScore W2551361256C149364088 @default.
- W2551361256 hasConceptScore W2551361256C154945302 @default.
- W2551361256 hasConceptScore W2551361256C165064840 @default.
- W2551361256 hasConceptScore W2551361256C185592680 @default.
- W2551361256 hasConceptScore W2551361256C204321447 @default.
- W2551361256 hasConceptScore W2551361256C2524010 @default.
- W2551361256 hasConceptScore W2551361256C2987255567 @default.
- W2551361256 hasConceptScore W2551361256C33923547 @default.
- W2551361256 hasConceptScore W2551361256C41008148 @default.
- W2551361256 hasConceptScore W2551361256C41608201 @default.
- W2551361256 hasConceptScore W2551361256C4554734 @default.
- W2551361256 hasConceptScore W2551361256C55493867 @default.
- W2551361256 hasConceptScore W2551361256C80444323 @default.
- W2551361256 hasConceptScore W2551361256C96711827 @default.
- W2551361256 hasLocation W25513612561 @default.
- W2551361256 hasLocation W25513612562 @default.
- W2551361256 hasOpenAccess W2551361256 @default.
- W2551361256 hasPrimaryLocation W25513612561 @default.
- W2551361256 hasRelatedWork W2551361256 @default.
- W2551361256 hasRelatedWork W2579831760 @default.
- W2551361256 hasRelatedWork W2784239688 @default.
- W2551361256 hasRelatedWork W2791913352 @default.
- W2551361256 hasRelatedWork W2885483808 @default.
- W2551361256 hasRelatedWork W2923818335 @default.
- W2551361256 hasRelatedWork W2949888133 @default.
- W2551361256 hasRelatedWork W2962819387 @default.
- W2551361256 hasRelatedWork W4226052512 @default.
- W2551361256 hasRelatedWork W4226361842 @default.
- W2551361256 isParatext "false" @default.
- W2551361256 isRetracted "false" @default.
- W2551361256 magId "2551361256" @default.
- W2551361256 workType "article" @default.