Nonparametric Bayesian Modeling for Automated Database Schema Matching

Conference · Thu Jan 01 00:00:00 EST 2015

DOI:https://doi.org/10.1109/ICMLA.2015.235· OSTI ID:1330510

Ferragut, Erik M ^[1]; Laska, Jason A ^[1]

---

1. 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

Related Subjects

probabilistic modeling
Bayesian
machine learning
schema matching