@article{ROLDAN202149,
  title = {TOMATE: A heuristic-based approach to extract data from HTML tables},
  journal = {Information Sciences},
  volume = {577},
  pages = {49-68},
  year = {2021},
  issn = {0020-0255},
  doi = {https://doi.org/10.1016/j.ins.2021.04.087},
  url = {https://www.sciencedirect.com/science/article/pii/S002002552100428X},
  author = {Juan C. Roldán and Patricia Jiménez and Pedro Szekely and Rafael Corchuelo},
  keywords = {HTML tables, Data extraction},
  urlPaper = {http://usc-isi-i2.github.io/papers/juan21-is.pdf},
  abstract = {Extracting data from user-friendly HTML tables is difficult because of their different layouts, formats, and encoding problems. In this article, we present a new proposal that first applies several pre-processing heuristics to clean the tables, then performs functional analysis, and finally applies some post-processing heuristics to produce the output. Our most important contribution is regarding functional analysis, which we address by projecting the cells onto a high-dimensional feature space in which a standard clustering technique is used to make the meta-data cells apart from the data cells. We experimented with two large repositories of real-world HTML tables and our results confirm that our proposal can extract data from them with an F1 score of 89.50% in just 0.09 CPU seconds per table. We confronted our proposal with several competitors and the statistical analysis confirmed its superiority in terms of effectiveness, while it keeps very competitive in terms of efficiency.}
}

{"_id":"YrHvpTspSEHbopeTf","bibbaseid":"roldn-jimnez-szekely-corchuelo-tomateaheuristicbasedapproachtoextractdatafromhtmltables-2021","author_short":["Roldán, J. C.","Jiménez, P.","Szekely, P.","Corchuelo, R."],"bibdata":{"bibtype":"article","type":"article","title":"TOMATE: A heuristic-based approach to extract data from HTML tables","journal":"Information Sciences","volume":"577","pages":"49-68","year":"2021","issn":"0020-0255","doi":"https://doi.org/10.1016/j.ins.2021.04.087","url":"https://www.sciencedirect.com/science/article/pii/S002002552100428X","author":[{"firstnames":["Juan","C."],"propositions":[],"lastnames":["Roldán"],"suffixes":[]},{"firstnames":["Patricia"],"propositions":[],"lastnames":["Jiménez"],"suffixes":[]},{"firstnames":["Pedro"],"propositions":[],"lastnames":["Szekely"],"suffixes":[]},{"firstnames":["Rafael"],"propositions":[],"lastnames":["Corchuelo"],"suffixes":[]}],"keywords":"HTML tables, Data extraction","urlpaper":"http://usc-isi-i2.github.io/papers/juan21-is.pdf","abstract":"Extracting data from user-friendly HTML tables is difficult because of their different layouts, formats, and encoding problems. In this article, we present a new proposal that first applies several pre-processing heuristics to clean the tables, then performs functional analysis, and finally applies some post-processing heuristics to produce the output. Our most important contribution is regarding functional analysis, which we address by projecting the cells onto a high-dimensional feature space in which a standard clustering technique is used to make the meta-data cells apart from the data cells. We experimented with two large repositories of real-world HTML tables and our results confirm that our proposal can extract data from them with an F1 score of 89.50% in just 0.09 CPU seconds per table. We confronted our proposal with several competitors and the statistical analysis confirmed its superiority in terms of effectiveness, while it keeps very competitive in terms of efficiency.","bibtex":"@article{ROLDAN202149,\n title = {TOMATE: A heuristic-based approach to extract data from HTML tables},\n journal = {Information Sciences},\n volume = {577},\n pages = {49-68},\n year = {2021},\n issn = {0020-0255},\n doi = {https://doi.org/10.1016/j.ins.2021.04.087},\n url = {https://www.sciencedirect.com/science/article/pii/S002002552100428X},\n author = {Juan C. Roldán and Patricia Jiménez and Pedro Szekely and Rafael Corchuelo},\n keywords = {HTML tables, Data extraction},\n urlPaper = {http://usc-isi-i2.github.io/papers/juan21-is.pdf},\n abstract = {Extracting data from user-friendly HTML tables is difficult because of their different layouts, formats, and encoding problems. In this article, we present a new proposal that first applies several pre-processing heuristics to clean the tables, then performs functional analysis, and finally applies some post-processing heuristics to produce the output. Our most important contribution is regarding functional analysis, which we address by projecting the cells onto a high-dimensional feature space in which a standard clustering technique is used to make the meta-data cells apart from the data cells. We experimented with two large repositories of real-world HTML tables and our results confirm that our proposal can extract data from them with an F1 score of 89.50% in just 0.09 CPU seconds per table. We confronted our proposal with several competitors and the statistical analysis confirmed its superiority in terms of effectiveness, while it keeps very competitive in terms of efficiency.}\n}\n\n","author_short":["Roldán, J. C.","Jiménez, P.","Szekely, P.","Corchuelo, R."],"bibbaseid":"roldn-jimnez-szekely-corchuelo-tomateaheuristicbasedapproachtoextractdatafromhtmltables-2021","role":"author","urls":{"Paper":"http://usc-isi-i2.github.io/papers/juan21-is.pdf"},"keyword":["HTML tables","Data extraction"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/f/YrJcqfPX9JrHSF3tz/pszekely.bib","dataSources":["Pbjv8MEHB89rzaK5a"],"keywords":["html tables","data extraction"],"search_terms":["tomate","heuristic","based","approach","extract","data","html","tables","roldán","jiménez","szekely","corchuelo"],"title":"TOMATE: A heuristic-based approach to extract data from HTML tables","year":2021}