@article {Vadrevu:1 May 2006:1468-4527:278,
	author = "Vadrevu, Srinivas",
	author = "Gelgi, Fatih",
	author = "Nagarajan, Saravanakumar",
	author = "Davulcu, Hasan",
	title = "Gathering meta-data and instances from object referral lists on the web",
	journal = "Online Information Review",
	volume = "30",
	year = "1 May 2006",
	abstract = "<B>Purpose</B> ? The purpose of this research is to automatically separate and extract meta-data and instance information from various link pages in the web, by utilizing presentation and linkage regularities on the web. <B>Design/methodology/approach</B> ? Research objectives have been achieved through an information extraction system called semantic partitioner that automatically organizes the content in each web page into a hierarchical structure, and an algorithm that interprets and translates these hierarchical structures into logical statements by distinguishing and representing the meta-data and their individual data instances. <B>Findings</B> ? Experimental results for the university domain with 12 computer science department web sites, comprising 361 individual faculty and course home pages indicate that the performance of the meta-data and instance extraction averages 85, 88 percent &#60;IT&#62;F&#60;/IT&#62;-measure, respectively. Our METEOR system achieves this performance without any domain specific engineering requirement. <B>Originality/value</B> ? Important contributions of the METEOR system presented in this paper are: it performs extraction without the assumption that the object instance pages are template-driven; it is domain independent and does not require any previously engineered domain ontology; and by interpreting the link pages, it can extract both meta-data, such as concept and attribute names and their relationships, as well as their instances with high accuracy.",
	pages = "278-296(19)",
	url = "http://www.ingentaconnect.com/content/mcb/264/2006/00000030/00000003/art00006"
	doi = "doi:10.1108/14684520610675807"
}