Automatic Selection of Training Examples for a Record Deduplication Method Based on Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8129

@Article{Goncalves:2010:JIDM,

• title = "Automatic Selection of Training Examples for a Record Deduplication Method Based on Genetic Programming",
• author = "Gabriel Silva Goncalves and Moises G. {de Carvalho} and Alberto H. F. Laender and Marcos Andre Goncalves",
• journal = "Journal of Information and Data Management",
• year = "2010",
• number = "2",
• volume = "1",
• pages = "213--228",
• month = jun,
• keywords = "genetic algorithms, genetic programming, replica identification, artificial intelligence",
• ISSN = "2178-7107",
• URL = "http://seer.lcc.ufmg.br/index.php/jidm/article/view/59",
• bibdate = "2010-11-03",
• bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/jidm/jidm1.html#GoncalvesCLG10",
• size = "16 pages",
• abstract = "Recently, machine learning techniques have been used to solve the record deduplication problem. However, these techniques require examples, manually generated in most cases, for training purposes. This hinders the use of such techniques because of the cost required to create the set of examples. In this article, we propose an approach based on a deterministic technique to automatically suggest training examples for a deduplication method based on genetic programming. Our experiments with synthetic datasets show that, by using only 15percent of the examples suggested by our approach, it is possible to achieve results in terms of F1 that are equivalent to those obtained when using all the examples, leading to savings in training time of up to 85percent",
• notes = "An official publication of the Brazilian Computer Society Special Interest Group on Databases",

}

Genetic Programming entries for Gabriel Silva Goncalves Moises G de Carvalho Alberto H F Laender Marcos Andre Goncalves

Citations