Automatic Synthesis of Regular Expressions from Examples

Created by W.Langdon from gp-bibliography.bib Revision:1.3963

@Article{Bartoli:2014:Computer,
  author =       "Alberto Bartoli and Giorgio Davanzo and 
                 Andrea {De Lorenzo} and Eric Medvet and Enrico Sorio",
  journal =      "IEEE Computer",
  title =        "Automatic Synthesis of Regular Expressions from
                 Examples",
  year =         "2014",
  month =        dec,
  volume =       "47",
  number =       "12",
  pages =        "72--80",
  keywords =     "genetic algorithms, genetic programming, text
                 extraction, NLP",
  ISSN =         "0018-9162",
  DOI =          "doi:10.1109/MC.2014.344",
  size =         "9 pages",
  abstract =     "We propose a system for the automatic generation of
                 regular expressions for text-extraction tasks. The user
                 describes the desired task only by means of a set of
                 labelled examples. The generated regexes may be used
                 with common engines such as those that are part of
                 Java, PHP, Perl and so on. Usage of the system does not
                 require any familiarity with regular expressions
                 syntax. We performed an extensive experimental
                 evaluation on 12 different extraction tasks applied to
                 real-world datasets. We obtained very good results in
                 terms of precision and recall, even in comparison to
                 earlier state-of-the-art proposals. Our results are
                 highly promising toward the achievement of a practical
                 surrogate for the specific skills required for
                 generating regular expressions, and significant as a
                 demonstration of what can be achieved with GP-based
                 approaches on modern IT technology.",
  notes =        "http://regex.inginf.units.it Levenshtein distance =
                 edit distance. NSGA-II.

                 'We transform a tree into a regular expression by means
                 of a depth-first post order visit'

                 Also known as \cite{6994453}",
}

Genetic Programming entries for Alberto Bartoli Giorgio Davanzo Andrea De Lorenzo Eric Medvet Enrico Sorio

Citations