Developments in Generic Entity Resolution

Abstract

Entity resolution (ER) is the problem of identifying which records in a database refer to the same entity. Although ER is a well-known problem, the rapid increase of data has made ER a challenging problem in many application areas ranging from resolving shopping items to counter-terrorism. The SERF project at Stanford focuses on providing scalable and accurate ER techniques that can be used across applications. We introduce generic ER and explain the recent advances made in our project.