Exploiting content redundancy for web information extraction.

@inproceedings{gulhane-2010-exploiting, author = {Pankaj Gulhane and Rajeev Rastogi and Srinivasan H. Sengamedu and Ashwin Tengli}, editor = {Michael Rappa and Paul Jones and Juliana Freire and Soumen Chakrabarti}, title = {{Exploiting content redundancy for web information extraction}}, booktitle = {{Proceedings of the 19th International Conference on World Wide Web, WWW 2010, Raleigh, North Carolina, USA, April 26-30, 2010}}, pages = {1105--1106}, publisher = {ACM}, year = {2010}, url = {https://doi.org/10.1145/1772690.1772826}, doi = {https://doi.org/10.1145/1772690.1772826} }