Detecting near-duplicates for web crawling.

@inproceedings{manku-2007-detecting, author = {Gurmeet Singh Manku and Arvind Jain and Anish Das Sarma}, editor = {Carey L. Williamson and Mary Ellen Zurko and Peter F. Patel-Schneider and Prashant J. Shenoy}, title = {{Detecting near-duplicates for web crawling}}, booktitle = {{Proceedings of the 16th International Conference on World Wide Web, WWW 2007, Banff, Alberta, Canada, May 8-12, 2007}}, pages = {141--150}, publisher = {ACM}, year = {2007}, url = {https://doi.org/10.1145/1242572.1242592}, doi = {https://doi.org/10.1145/1242572.1242592} }