Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313200546> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4313200546 endingPage "212" @default.
- W4313200546 startingPage "199" @default.
- W4313200546 abstract "Knowledge Graphs (KGs) are among the most commonly used knowledge representation paradigms, being at the core of tasks such as question answering or recommendation systems. Knowledge Graph Completion (KGC) is one of the key tasks concerning KGs, where the goal is to extract new elements from the existing information. Different approaches have been proposed through the years to tackle this challenge. Among them, two analogous categories can be distinguished: rule-learning and Knowledge Graph Embeddings (KGE). Different methods have been subsequently proposed to unify both types under a single framework, such that the benefits of both proposals can be exploited. However, most of these methods consider using rule-learning models as a boosting agent for KGE models, but not as an explainability tool. This work presents GEnI1, a framework capable of generating insights and explanations for KGE models. GEnI follows a three-phase sequential process, generating a feasible explanation for a given prediction. Possible outcomes are rules, correlations, and influence detection. Moreover, the output is expressed in natural language to further extend the explainability of the proposal. GEnI has been successfully evaluated under three criteria: coherence, the meaningfulness of the output, and reliability. Moreover, it can be used by both translational and bilinear KGE models, offering broad coverage. Furthermore, this work also presents an in-depth review of existing integrative approaches between rule-learning and embedding models, providing a comparative framework between them." @default.
- W4313200546 created "2023-01-06" @default.
- W4313200546 creator A5005744973 @default.
- W4313200546 creator A5021195199 @default.
- W4313200546 creator A5059845936 @default.
- W4313200546 date "2023-02-01" @default.
- W4313200546 modified "2023-10-18" @default.
- W4313200546 title "GEnI: A framework for the generation of explanations and insights of knowledge graph embedding predictions" @default.
- W4313200546 cites W2022166150 @default.
- W4313200546 cites W2094728533 @default.
- W4313200546 cites W2107306718 @default.
- W4313200546 cites W2158028897 @default.
- W4313200546 cites W2250911766 @default.
- W4313200546 cites W2460423734 @default.
- W4313200546 cites W2563063592 @default.
- W4313200546 cites W2604314403 @default.
- W4313200546 cites W2728059831 @default.
- W4313200546 cites W2774837955 @default.
- W4313200546 cites W2920008855 @default.
- W4313200546 cites W2949972983 @default.
- W4313200546 cites W2950604577 @default.
- W4313200546 cites W2951105272 @default.
- W4313200546 cites W2963149704 @default.
- W4313200546 cites W2965653989 @default.
- W4313200546 cites W2966298461 @default.
- W4313200546 cites W2974737854 @default.
- W4313200546 cites W2994043269 @default.
- W4313200546 cites W2997932512 @default.
- W4313200546 cites W3008392753 @default.
- W4313200546 cites W3013899790 @default.
- W4313200546 cites W3032634531 @default.
- W4313200546 cites W3094076810 @default.
- W4313200546 cites W3094233825 @default.
- W4313200546 cites W3106176046 @default.
- W4313200546 cites W3106706183 @default.
- W4313200546 cites W3120491054 @default.
- W4313200546 cites W3129070541 @default.
- W4313200546 cites W3130062726 @default.
- W4313200546 cites W3208791567 @default.
- W4313200546 cites W4306317717 @default.
- W4313200546 doi "https://doi.org/10.1016/j.neucom.2022.12.010" @default.
- W4313200546 hasPublicationYear "2023" @default.
- W4313200546 type Work @default.
- W4313200546 citedByCount "2" @default.
- W4313200546 countsByYear W43132005462023 @default.
- W4313200546 crossrefType "journal-article" @default.
- W4313200546 hasAuthorship W4313200546A5005744973 @default.
- W4313200546 hasAuthorship W4313200546A5021195199 @default.
- W4313200546 hasAuthorship W4313200546A5059845936 @default.
- W4313200546 hasConcept C105795698 @default.
- W4313200546 hasConcept C119857082 @default.
- W4313200546 hasConcept C132525143 @default.
- W4313200546 hasConcept C154945302 @default.
- W4313200546 hasConcept C2781181686 @default.
- W4313200546 hasConcept C2987255567 @default.
- W4313200546 hasConcept C33923547 @default.
- W4313200546 hasConcept C41008148 @default.
- W4313200546 hasConcept C41608201 @default.
- W4313200546 hasConcept C44291984 @default.
- W4313200546 hasConcept C46686674 @default.
- W4313200546 hasConcept C80444323 @default.
- W4313200546 hasConceptScore W4313200546C105795698 @default.
- W4313200546 hasConceptScore W4313200546C119857082 @default.
- W4313200546 hasConceptScore W4313200546C132525143 @default.
- W4313200546 hasConceptScore W4313200546C154945302 @default.
- W4313200546 hasConceptScore W4313200546C2781181686 @default.
- W4313200546 hasConceptScore W4313200546C2987255567 @default.
- W4313200546 hasConceptScore W4313200546C33923547 @default.
- W4313200546 hasConceptScore W4313200546C41008148 @default.
- W4313200546 hasConceptScore W4313200546C41608201 @default.
- W4313200546 hasConceptScore W4313200546C44291984 @default.
- W4313200546 hasConceptScore W4313200546C46686674 @default.
- W4313200546 hasConceptScore W4313200546C80444323 @default.
- W4313200546 hasFunder F4320313831 @default.
- W4313200546 hasFunder F4320322138 @default.
- W4313200546 hasFunder F4320335598 @default.
- W4313200546 hasLocation W43132005461 @default.
- W4313200546 hasOpenAccess W4313200546 @default.
- W4313200546 hasPrimaryLocation W43132005461 @default.
- W4313200546 hasRelatedWork W1987859285 @default.
- W4313200546 hasRelatedWork W1996541855 @default.
- W4313200546 hasRelatedWork W2923818335 @default.
- W4313200546 hasRelatedWork W3211210768 @default.
- W4313200546 hasRelatedWork W4200450299 @default.
- W4313200546 hasRelatedWork W4226361842 @default.
- W4313200546 hasRelatedWork W4310879833 @default.
- W4313200546 hasRelatedWork W4313488044 @default.
- W4313200546 hasRelatedWork W4385279070 @default.
- W4313200546 hasRelatedWork W3129794543 @default.
- W4313200546 hasVolume "521" @default.
- W4313200546 isParatext "false" @default.
- W4313200546 isRetracted "false" @default.
- W4313200546 workType "article" @default.