%0 Conference Paper %1 Frobe2021-bz %A Fröbe, Maik %A Bevendorff, Janek %A Gienapp, Lukas %A Völske, Michael %A Stein, Benno %A Potthast, Martin %A Hagen, Matthias %B Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval %C New York, NY, USA %D 2021 %I ACM %K %T CopyCat: Near-duplicates within and between the ClueWeb and the common crawl

@inproceedings{Frobe2021-bz, added-at = {2024-12-09T09:29:34.000+0100}, address = {New York, NY, USA}, author = {Fr{\"o}be, Maik and Bevendorff, Janek and Gienapp, Lukas and V{\"o}lske, Michael and Stein, Benno and Potthast, Martin and Hagen, Matthias}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/291050ba28e5dd12ae7e1f8b16bcc6311/lugi004g}, booktitle = {Proceedings of the 44th International {ACM} {SIGIR} Conference on Research and Development in Information Retrieval}, conference = {SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval}, interhash = {7a4beb1e4f7270d8d76a9f2ba8b4068c}, intrahash = {91050ba28e5dd12ae7e1f8b16bcc6311}, keywords = {}, location = {Virtual Event Canada}, month = {07}, publisher = {ACM}, timestamp = {2024-12-09T09:29:34.000+0100}, title = {{CopyCat}: Near-duplicates within and between the {ClueWeb} and the common crawl}, year = 2021 }