A Survey on Entity Resolution

PhD Qualifying Examination


Title: "A Survey on Entity Resolution"

Miss Xiaoheng Xie


Abstract:

Entity Resolution (ER) identifies and merges records which refer to the 
same real-world entity. Since entities in the real world often have 
multiple representations in different data sources, these duplicate 
records may not easily be merged because of some errors in the description 
or different formats. Consequently, entity resolution is focused on how to 
detect these duplicate records. In this paper, we present a survey on 
entity resolution approaches. First, we give a brief introduction of 
entity resolution and then review the process of entity resolution, 
including some simple and popular metrics for measuring similarity and 
methods for detecting duplication. Then, we concentrate on the problem of 
how to improve the efficiency of entity resolution methods. We cover 
several significant approaches for improving entity resolution efficiency 
and scalability. Finally, we describe some composition tools for entity 
resolution.


Date:     		Thursday, 14 January 2010

Time:                   3:00pm - 5:00pm

Venue:                  Room 3501
 			lifts 25/26

Committee Members:      Prof. Frederick Lochovsky (Supervisor)
 			Dr. Lei Chen (Chairperson)
 			Prof. Dik-Lun Lee
 			Dr. Raymond Wong


**** ALL are Welcome ****