Learning Text Patterns using Separate-and-Conquer Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Bartoli:2015:EuroGP,

• author = "Alberto Bartoli and Andrea {De Lorenzo} and Eric Medvet and Fabiano Tarlao",
• title = "Learning Text Patterns using Separate-and-Conquer Genetic Programming",
• booktitle = "18th European Conference on Genetic Programming",
• year = "2015",
• editor = "Penousal Machado and Malcolm I. Heywood and James McDermott and Mauro Castelli and Pablo Garcia-Sanchez and Paolo Burelli and Sebastian Risi and Kevin Sim",
• series = "LNCS",
• volume = "9025",
• publisher = "Springer",
• pages = "16--27",
• address = "Copenhagen",
• month = "8-10 " # apr,
• organisation = "EvoStar",
• keywords = "genetic algorithms, genetic programming, Regular expressions, Multiple pattern, Programming by example, Text extraction",
• isbn13 = "978-3-319-16500-4",
• DOI = "doi:10.1007/978-3-319-16501-1_2",
• abstract = "The problem of extracting knowledge from large volumes of unstructured textual information has become increasingly important. We consider the problem of extracting text slices that adhere to a syntactic pattern and propose an approach capable of generating the desired pattern automatically, from a few annotated examples. Our approach is based on Genetic Programming and generates extraction patterns in the form of regular expressions that may be input to existing engines without any post-processing. Key feature of our proposal is its ability of discovering automatically whether the extraction task may be solved by a single pattern, or rather a set of multiple patterns is required. We obtain this property by means of a separate-and-conquer strategy: once a candidate pattern provides adequate performance on a subset of the examples, the pattern is inserted into the set of final solutions and the evolutionary search continues on a smaller set of examples including only those not yet solved adequately. Our proposal outperforms an earlier state-of-the-art approach on three challenging datasets",
• notes = "Part of \cite{Machado:2015:GP} EuroGP'2015 held in conjunction with EvoCOP2015, EvoMusArt2015 and EvoApplications2015",

}

Genetic Programming entries for Alberto Bartoli Andrea De Lorenzo Eric Medvet Fabiano Tarlao

Citations