@inproceedings{biblio6020163794903877689, author = {Miroslav Spousta and Michal Marek and Pavel Pecina}, year = 2008, title = {Victor: the Web-Page Cleaning Tool}, booktitle = {Proceedings of the 4th Web as Corpus Workshop}, pages = {12--17}, publisher = {ACL SIGWAC}, address = {Marrakech, Morocco}, isbn = {2-9517408-4-0}, }