Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Large-scale collective entity matching

Rastogi Vibhor, Dalvi Nilesh, Garofalakis Minos

Full record


URI: http://purl.tuc.gr/dl/dias/284C74C9-4024-4E15-9E13-754BFF15CE0D
Year 2009
Type of Item Conference Full Paper
License
Details
Bibliographic Citation V. Rastogi, N. Dalvi and M. Garofalakis, "Large-scale collective entity matching", in 35th International Conference on Very Large Data Bases, 2009. https://doi.org/10.14778/1938545.1938546
Appears in Collections

Summary

There have been several recent advancements in Machine Learningcommunity on the Entity Matching (EM) problem. However,their lack of scalability has prevented them from being applied inpractical settings on large real-life datasets. Towards this end, wepropose a principled framework to scale any generic EM algorithm.Our technique consists of running multiple instances of the EM algorithmon small neighborhoods of the data and passing messagesacross neighborhoods to construct a global solution. We prove formalproperties of our framework and experimentally demonstratethe effectiveness of our approach in scaling EM algorithms.

Services

Statistics