What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarization
Caleb Belth, Xinyi Zheng, Jilles Vreeken, Danai Koutra
Abstract
Knowledge graphs (KGs) store highly heterogeneous information about the world in the structure of a graph, and are useful for tasks such as question answering and reasoning. However, they often contain errors and are missing information. Vibrant research in KG refinement has worked to resolve these issues, tailoring techniques to either detect specific types of errors or complete a KG.
Topics & Concepts
Automatic summarizationComputer scienceQuestion answeringArtificial intelligenceMissing dataData miningNatural language processingCharacterization (materials science)Relation (database)Information retrievalComponent (thermodynamics)Machine learningKnowledge graphKnowledge extractionKey (lock)Knowledge baseKnowledge-based systemsTraining setAdvanced Graph Neural NetworksTopic ModelingNatural Language Processing Techniques