Exploiting relationships for domain-independent data cleaning.

Appeared in SIAM Data Mining (SDM) 2005 Conference

Dmitri V. Kalashnikov, Sharad Mehrotra, and Zhaoqi Chen

Computer Science Department
University of California, Irvine
GDF project (http://www.ics.uci.edu/~dvk/GDF)


In this paper we address the problem of reference disambiguation. Specifically, we consider a situation where entities in the database are referred to using descriptions (e.g., a set of instantiated attributes). The objective of reference disambiguation is to identify the unique entity to which each description corresponds. The key difference between the approach we propose and the traditional techniques is that our approach analyzes not only object features but also inter-object relationships to improve the disambiguation quality. Our extensive experiments over two real data sets and also over synthetic datasets show that analysis of relationships significantly improves quality of the result.

Categories and Subject Descriptors:

H.2.m [Database Management]: Miscellaneous - Data cleaning;
H.2.8 [Database Management]: Database Applications - Data mining;
H.2.5 [Information Systems]: Heterogeneous Databases;
H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval


GDF, relationship-based data cleaning, reference disambiguation, record linkage, data mining, iterative data cleaning

Downloadable files:

Paper: SDM05_dvk.12page.pdf
Paper: TODS06 (extended version 1)
Paper: SDM05_TR (extended version 2)
Presentation: SDM05_dvk.ppt
Source Code: Code

BibTeX entry:

   author    = {Dmitri V. Kalashnikov and Sharad Mehrotra and Zhaoqi Chen},                 
   title     = {Exploiting relationships for domain-independent data cleaning},
   booktitle = {SIAM International Conference on Data Mining (SIAM SDM)},
   year      = {2005},
   month     = {April 21--23},
   address   = {Newport Beach, CA, USA}
Back to Kalashnikov's homepage