GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Marko Bekavac and Jan Snajder",
  title =        "GPKEX: Genetically Programmed Keyphrase Extraction
                 from Croatian Texts",
  booktitle =    "Proceedings of the 4th Biennial International Workshop
                 on Balto-Slavic Natural Language Processing",
  year =         "2013",
  editor =       "Jakub Piskorski and Lidia Pivovarova and 
                 Hristo Tanev and Roman Yangarber",
  pages =        "43--47",
  address =      "Sofia, Bulgaria",
  publisher_address = "209 N. Eighth Street Stroudsburg, PA 18360 USA
                 Tel: +1-570-476-8006 Fax: +1-570-476-0860
  month =        "8-9 " # aug,
  publisher =    "Association for Computational Linguistics",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-1-937284-59-6",
  language =     "en",
  oai =          "oai:CiteSeerX.psu:",
  URL =          "",
  URL =          "",
  URL =          "",
  size =         "5 pages",
  abstract =     "We describe GPKEX, a key-phrase extraction method
                 based on genetic programming. We represent Keyphrase
                 scoring measures as syntax trees and evolve them to
                 produce rankings for key phrase candidates extracted
                 from text. We apply and evaluate GPKEX on Croatian
                 newspaper articles. We show that GPKEX can evolve
                 simple and interpretable key-phrase scoring measures
                 that perform comparably to more complex machine
                 learning methods previously developed for Croatian.",
  notes =        "The annotated dataset is available under CC BY-NC-SA
                 license from

                 ACL 2013


Genetic Programming entries for Marko Bekavac Jan Snajder