Predicting the effectiveness of pattern-based entity extractor inference

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

@Article{Bartoli:2016:ASC,

• author = "Alberto Bartoli and Andrea {De Lorenzo} and Eric Medvet and Fabiano Tarlao",
• title = "Predicting the effectiveness of pattern-based entity extractor inference",
• journal = "Applied Soft Computing",
• volume = "46",
• pages = "398--406",
• year = "2016",
• ISSN = "1568-4946",
• DOI = "doi:10.1016/j.asoc.2016.05.023",
• URL = "http://www.sciencedirect.com/science/article/pii/S1568494616302241",
• abstract = "An essential component of any workflow leveraging digital data consists in the identification and extraction of relevant patterns from a data stream. We consider a scenario in which an extraction inference engine generates an entity extractor automatically from examples of the desired behaviour, which take the form of user-provided annotations of the entities to be extracted from a dataset. We propose a methodology for predicting the accuracy of the extractor that may be inferred from the available examples. We propose several prediction techniques and analyse experimentally our proposals in great depth, with reference to extractors consisting of regular expressions. The results suggest that reliable predictions for tasks of practical complexity may indeed be obtained quickly and without actually generating the entity extractor.",
• keywords = "genetic algorithms, genetic programming, String similarity metrics, Information extraction, Hardness estimation",

}

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

Citations