@inproceedings{gibson-etal-2008-identification, title = "Identification of Duplicate News Stories in Web Pages", author = "Gibson, John and Wellner, Ben and Lubar, Susan", editor = "Evert, Stefan and Kilgarriff, Adam and Sharoff, Serge", booktitle = "Proceedings of the 4th Web as Corpus Workshop", month = jun, year = "2008", address = "Marrakech, Morocco", publisher = "European Language Resources Association", url = "https://preview.aclanthology.org/fix-sig-urls/2008.wac-1.5/", pages = "26--33" }