Learning to deduplicate

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{deCarvalho:2006:JCDL,
  author =       "Moises G. {de Carvalho} and Marcos Andre Goncalves and 
                 Alberto H. F. Laender and Altigran S. {da Silva}",
  title =        "Learning to deduplicate",
  booktitle =    "Proceedings of the 6th ACM/IEEE-CS Joint Conference on
                 Digital Libraries, JCDL '06",
  year =         "2006",
  pages =        "41--50",
  address =      "Chapel Hill, NC, USA",
  month =        jun,
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming,
                 Deduplication, Digital Libraries",
  ISBN =         "1-59593-354-9",
  URL =          "http://delivery.acm.org/10.1145/1150000/1141760/p41-decarvalho.pdf?key1=1141760&key2=6906456911&coll=GUIDE&dl=GUIDE&CFID=45325455&CFTOKEN=75817203",
  DOI =          "doi:10.1145/1141753.1141760",
  size =         "10 pages",
  abstract =     "Identifying record replicas in digital libraries and
                 other types of digital repositories is fundamental to
                 improve the quality of their content and services as
                 well as to yield eventual sharing efforts. Several
                 deduplication strategies are available, but most of
                 them rely on manually chosen settings to combine
                 evidence used to identify records as being replicas. In
                 this paper, we present the results of experiments we
                 have carried out with a novel machine learning approach
                 we have proposed for the de duplication problem. This
                 approach, based on genetic programming (GP), is able to
                 automatically generate similarity functions to identify
                 record replicas in a given repository. The generated
                 similarity functions properly combine and weight the
                 best evidence available among the record fields in
                 order to tell when two distinct records represent the
                 same real-world entity. The results of the experiments
                 show that our approach outperforms the baseline method
                 by Fellegi and Sunter by more than 12percent when
                 identifying replicas in a data set containing
                 researcher's personal data, and by more than 7percent,
                 in a data set with article citation data",
  notes =        "Comput. Sci. Dept., Fed. Univ. of Minas Gerais, Belo
                 Horizonte",
}

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

Citations