Publication Type
Conference Paper
Publication Date
Page Numbers
82 to 88
Conference Name
International Conference on Machine Learning Applications
Conference Location
Miami, Florida, United States of America
Conference Sponsor
IEEE
Conference Date
-
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.