Nonparametric Bayesian Modeling for Automated Database Schema Matching

TL;DR

This paper presents a nonparametric Bayesian framework for automated database schema matching, improving accuracy and speed over existing methods by modeling fields probabilistically.

Contribution

It introduces a novel nonparametric Bayesian approach to schema matching that effectively compares field distributions for better accuracy.

Findings

More accurate than existing instance-based algorithms

Faster matching process

Effective in merging databases

Abstract

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.