Correcting Knowledge Base Assertions
Chen, Jiaoyan, Chen, Xi, Horrocks, Ian, Jimenez-Ruiz, Ernesto, Myklebust, Erik Bryhn
Abstract
The usefulness and usability of knowledge bases (KBs) is often limited by quality issues. One common issue is the presence of erroneous assertions, often caused by lexical or semantic confusion. We study the problem of correcting such assertions, and present a general correction framework which combines lexical matching, semantic embedding, soft constraint mining and semantic consistency checking. The framework is evaluated using DBpedia and an enterprise medical KB.
Topics & Concepts
Computer scienceEmbeddingNatural language processingConsistency (knowledge bases)Semantic equivalenceConfusionKnowledge baseConstraint (computer-aided design)Information retrievalUsabilityArtificial intelligenceSemantics (computer science)Semantic computingProgramming languageSemantic WebHuman–computer interactionMathematicsGeometryPsychologyPsychoanalysisSemantic Web and OntologiesNatural Language Processing TechniquesTopic Modeling