Nonparametric Bayesian Modeling for Automated Database Schema Matching
- ORNL
The problem of merging databases arises in many government and commercial applications. Schema matching, a common first step, identifies equivalent fields between databases. We introduce a schema matching framework that builds nonparametric Bayesian models for each field and compares them by computing the probability that a single model could have generated both fields. Our experiments show that our method is more accurate and faster than the existing instance-based matching algorithms in part because of the use of nonparametric Bayesian models.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1330510
- Resource Relation:
- Conference: International Conference on Machine Learning Applications, Miami, FL, USA, 20151209, 20151211
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Nonparametric Bayesian Approach For Emission Tomography Reconstruction
ENHANCING SEISMIC CALIBRATION RESEARCH THROUGH SOFTWARE AUTOMATION AND SCIENTIFIC INFORMATION MANAGEMENT
Unsupervised Group Discovery and LInk Prediction in Relational Datasets: a nonparametric Bayesian approach
Journal Article
·
Tue Nov 13 00:00:00 EST 2007
· AIP Conference Proceedings
·
OSTI ID:1330510
ENHANCING SEISMIC CALIBRATION RESEARCH THROUGH SOFTWARE AUTOMATION AND SCIENTIFIC INFORMATION MANAGEMENT
Conference
·
Thu Jul 03 00:00:00 EDT 2008
·
OSTI ID:1330510
+2 more
Unsupervised Group Discovery and LInk Prediction in Relational Datasets: a nonparametric Bayesian approach
Technical Report
·
Thu May 03 00:00:00 EDT 2007
·
OSTI ID:1330510