Urd: A Data Summarization Tool for the Acquisition of Meaningful Cardinality Constraints with Probabilistic Intervals
Tania Roblot, Sebastian Link · 2017
With an ever-growing number of applications producing uncertain data, the probabilistic data model has gained renewed attention. Probabilistic cardinality constraints stipulate a range on the marginal probability by which cardinality constraints hold in probabilistic databases. The core challenge is in identifying the bounds that are meaningful in a given application domain. Our tool helps data and domain experts jointly tackle that challenge. The demo showcases our prototype, which computes perfect data summarizations for any set of probabilistic cardinality constraints: Armstrong databases.