- author = "Alberto Bartoli and Andrea {De Lorenzo} and Eric Medvet and Fabiano Tarlao",
- title = "Regex-based Entity Extraction with Active Learning and Genetic Programming",
- journal = "ACM SIGAPP Applied Computing Review",
- year = "2016",
- volume = "16",
- number = "2",
- pages = "7--15",
- month = jun,
- keywords = "genetic algorithms, genetic programming, entity extraction, information extraction, machine learning, programming by examples",
- publisher = "ACM",
- address = "New York, NY, USA",
- ISSN = "1559-6915",
-
URL = "
https://sites.google.com/site/machinelearningts/publications/international-journal-publications/regex-basedentityextractionwithactivelearningandgeneticprogramming/2016-ACR-RegexEntityExtractionActiveLearningGP.pdf",
-
URL = "
http://doi.acm.org/10.1145/2993231.2993232",
-
DOI = "
doi:10.1145/2993231.2993232",
- acmid = "2993232",
- size = "9 pages",
-
abstract = "We consider the long-standing problem of the automatic
generation of regular expressions for text extraction,
based solely on examples of the desired behaviour. We
investigate several active learning approaches in which
the user annotates only one desired extraction and then
merely answers extraction queries generated by the
system.
The resulting framework is attractive because it is the system, not the user, which digs out the data in search of the samples most suitable to the specific learning task. We tailor our proposals to a state-of-the-art learner based on Genetic Programming and we assess them experimentally on a number of challenging tasks of realistic complexity. The results indicate that active learning is indeed a viable framework in this application domain and may thus significantly decrease the amount of costly annotation effort required.",
-
notes = "See \cite{conf/sac/BartoliLMT16}.
Also known as \cite{Bartoli:2016:REE:2993231.2993232}",
