Neural Knowledge Base Repairs
| Autor: | Fabian M. Suchanek, Thomas Pellissier Tanon |
|---|---|
| Přispěvatelé: | Data, Intelligence and Graphs (DIG), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Informatique et Réseaux (INFRES), Télécom ParisTech, Institut Polytechnique de Paris (IP Paris) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Computer science business.industry Deep learning [INFO.INFO-WB]Computer Science [cs]/Web 02 engineering and technology Machine learning computer.software_genre Task (project management) [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] Constraint (information theory) Knowledge base 020204 information systems Web page 0202 electrical engineering electronic engineering information engineering Graph (abstract data type) Literal (computer programming) 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | The Semantic Web 18th International Conference, ESWC 2021, Virtual Event, June 6–10, 2021, Proceedings European Semantic Web Conference European Semantic Web Conference, Jun 2021, Hersonissos (virtual), Greece. pp.287-303, ⟨10.1007/978-3-030-77385-4_17⟩ The Semantic Web ISBN: 9783030773847 ESWC |
| Popis: | International audience; The curation of a knowledge base is a crucial but costly task. In this work, we suggest to make use of the advances in neural network research to improve the automated correction of constraint violations. Our method is a deep learning refinement of "Learning how to correct a knowledge base from the edit history", and similarly uses the edits that solved some violations in the past to infer how to solve similar violations in the present. Our system makes use of the graph content, literal embeddings, and features extracted from Web pages to improve its performance. The experimental evaluation on Wikidata shows significant improvements over baselines. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|