A pattern tree-based approach to learning URL normalization rules.

@inproceedings{lei-2010-pattern, author = {Tao Lei and Rui Cai and Jiang-Ming Yang and Yan Ke and Xiaodong Fan and Lei Zhang}, editor = {Michael Rappa and Paul Jones and Juliana Freire and Soumen Chakrabarti}, title = {{A pattern tree-based approach to learning URL normalization rules}}, booktitle = {{Proceedings of the 19th International Conference on World Wide Web, WWW 2010, Raleigh, North Carolina, USA, April 26-30, 2010}}, pages = {611--620}, publisher = {ACM}, year = {2010}, url = {https://doi.org/10.1145/1772690.1772753}, doi = {https://doi.org/10.1145/1772690.1772753} }