A Large Scale Name Matching and Search Framework

The ability of identifying whether two strings represent names referring to the same real world entity is essential for avoiding information integration problems, such as duplication of records. We study this problem in a scenario where the amount of data to analyze becomes large. Our purpose is to develop a framework that address the name match and search problem, combining together different strategies, and is able to consider also the semantic of the string representing a name. Moreover we propose a dataset for evaluating name matching algorithm which consider semantic variation of names.