Learning URL patterns for webpage de-duplication.

@inproceedings{koppula-2010-learning, author = {Hema Swetha Koppula and Krishna P. Leela and Amit Agarwal and Krishna Prasad Chitrapura and Sachin Garg and Amit Sasturkar}, editor = {Brian D. Davison and Torsten Suel and Nick Craswell and Bing Liu}, title = {{Learning URL patterns for webpage de-duplication}}, booktitle = {{Proceedings of the Third International Conference on Web Search and Web Data Mining, WSDM 2010, New York, NY, USA, February 4-6, 2010}}, pages = {381--390}, publisher = {ACM}, year = {2010}, url = {https://doi.org/10.1145/1718487.1718535}, doi = {https://doi.org/10.1145/1718487.1718535} }