Schema Matching using Machine Learning

TL;DR

This paper presents a hybrid machine learning approach for schema matching that combines data and schema names, introduces a global dictionary for one-to-many matching, and compares different methods based on performance metrics.

Contribution

It introduces a novel hybrid approach utilizing data and schema names, along with a global dictionary, for improved schema matching.

Findings

The hybrid approach achieves competitive F-scores, precision, and recall.

Comparison shows advantages over previous methods.

Global dictionary enhances one-to-many schema matching.

Abstract

Schema Matching is a method of finding attributes that are either similar to each other linguistically or represent the same information. In this project, we take a hybrid approach at solving this problem by making use of both the provided data and the schema name to perform one to one schema matching and introduce the creation of a global dictionary to achieve one to many schema matching. We experiment with two methods of one to one matching and compare both based on their F-scores, precision, and recall. We also compare our method with the ones previously suggested and highlight differences between them.