Mining data records in Web pages Export

@inproceedings{citeulike:494093, abstract = {A large amount of information on the Web is contained in regularly structured objects, which we call data records. Such data records are important because they often present the essential information of their host pages, e.g., lists of products or services. It is useful to mine such data records in order to extract information from them to provide value-added services. Existing automatic techniques are not satisfactory because of their poor accuracies. In this paper, we propose a more effective technique to perform the task. The technique is based on two observations about data records on the Web and a string matching algorithm. The proposed technique is able to mine both contiguous and non-contiguous data records. Our experimental results show that the proposed technique outperforms existing techniques substantially.}, address = {New York, NY, USA}, author = {Liu, Bing and Grossman, Robert and Zhai, Yanhong}, booktitle = {KDD '03: Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {494093}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=956826}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/956750.956826}, doi = {10.1145/956750.956826}, isbn = {1-58113-737-0}, keywords = {2003, record\_extraction}, location = {Washington, D.C.}, pages = {601--606}, posted-at = {2007-10-12 05:14:58}, priority = {5}, publisher = {ACM}, title = {Mining data records in Web pages}, url = {http://dx.doi.org/10.1145/956750.956826}, year = {2003} }

TY - CONF ID - citeulike:494093 L3 - citeulike-article-id:494093 N2 - A large amount of information on the Web is contained in regularly structured objects, which we call data records. Such data records are important because they often present the essential information of their host pages, e.g., lists of products or services. It is useful to mine such data records in order to extract information from them to provide value-added services. Existing automatic techniques are not satisfactory because of their poor accuracies. In this paper, we propose a more effective technique to perform the task. The technique is based on two observations about data records on the Web and a string matching algorithm. The proposed technique is able to mine both contiguous and non-contiguous data records. Our experimental results show that the proposed technique outperforms existing techniques substantially. CY - Washington, D.C. SN - 1-58113-737-0 AD - New York, NY, USA EP - 606 TI - Mining data records in Web pages PB - ACM T2 - KDD '03: Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining SP - 601 KW - 2003 KW - record_extraction AU - Liu, Bing AU - Grossman, Robert AU - Zhai, Yanhong PY - 2003/// UR - http://dx.doi.org/10.1145/956750.956826 ER -