@inproceedings{9a16041690194742825f07c7de83f8ea,
title = "FiVaTech: Page-level web data extraction from template pages",
abstract = "In this paper, we proposed a new approach, called FiVaTech for the problem of Web data extraction. FiVaTech is a page-level data extraction system which deduces the data schema and templates for the input pages generated from a CGI program. FiVaTech uses tree templates to model the generation of dynamic Web pages. FiVaTech can deduce the schema and templates for each individual Deep Web site, which contains either singleton or multiple data records in one Web page. FiVaTech applies tree matching, tree alignment, and mining techniques to achieve the challenging task. The experiments show an encouraging result for the test pages used in many state-of-the-art Web data extraction works.",
author = "Mohammed Kayed and Khaled Shaalan and Chang, {Chia Hui} and Girgis, {Moheb Ramzy}",
year = "2007",
doi = "10.1109/ICDMW.2007.95",
language = "???core.languages.en_GB???",
isbn = "0769530192",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
pages = "15--20",
booktitle = "ICDM Workshops 2007 - Proceedings of the 17th IEEE International Conference on Data Mining Workshops",
note = "17th IEEE International Conference on Data Mining Workshops, ICDM Workshops 2007 ; Conference date: 28-10-2007 Through 31-10-2007",
}