@inproceedings{
Title = {Page-level Template Detection via Isotonic Smoothing},
Booktitle = {16th International World Wide Web Conference (WWW2007)},
Year = {2007},
Month = {May},
Abstract = {We develop a novel framework for the ``page-level'' template detection problem.  Our framework is built on two main ideas.  The first is the automatic generation of training data for a classifier that, given a page, assigns a templateness score to every DOM node of the page.  The second is the global smoothing of these per-node classifier scores by solving a regularized isotonic regression problem; the latter follows from a simple yet powerful abstraction of templateness on a page.  Our extensive experiments on human-labeled test data show that our approach detects templates effectively.},
Url = {http://data.semanticweb.org/conference/www/2007/paper/main/588}
}