%0 Conference Paper %1 Bing:2014:WPS:2600428.2609630 %A Bing, Lidong %A Guo, Rui %A Lam, Wai %A Niu, Zheng-Yu %A Wang, Haifeng %B Proceedings of the 37th International ACM SIGIR Conference on Research &\#38; Development in Information Retrieval %C New York, NY, USA %D 2014 %I ACM %K classification page prediction segmentation structured web %P 767--776 %R 10.1145/2600428.2609630 %T Web Page Segmentation with Structured Prediction and Its Application in Web Page Classification %U http://doi.acm.org/10.1145/2600428.2609630 %X We propose a framework which can perform Web page segmentation with a structured prediction approach. It formulates the segmentation task as a structured labeling problem on a transformed Web page segmentation graph (WPS-graph). WPS-graph models the candidate segmentation boundaries of a page and the dependency relation among the adjacent segmentation boundaries. Each labeling scheme on the WPS-graph corresponds to a possible segmentation of the page. The task of finding the optimal labeling of the WPS-graph is transformed into a binary Integer Linear Programming problem, which considers the entire WPS-graph as a whole to conduct structured prediction. A learning algorithm based on the structured output Support Vector Machine framework is developed to determine the feature weights, which is capable to consider the inter-dependency among candidate segmentation boundaries. Furthermore, we investigate its efficacy in supporting the development of automatic Web page classification. %@ 978-1-4503-2257-7

@inproceedings{Bing:2014:WPS:2600428.2609630, abstract = {We propose a framework which can perform Web page segmentation with a structured prediction approach. It formulates the segmentation task as a structured labeling problem on a transformed Web page segmentation graph (WPS-graph). WPS-graph models the candidate segmentation boundaries of a page and the dependency relation among the adjacent segmentation boundaries. Each labeling scheme on the WPS-graph corresponds to a possible segmentation of the page. The task of finding the optimal labeling of the WPS-graph is transformed into a binary Integer Linear Programming problem, which considers the entire WPS-graph as a whole to conduct structured prediction. A learning algorithm based on the structured output Support Vector Machine framework is developed to determine the feature weights, which is capable to consider the inter-dependency among candidate segmentation boundaries. Furthermore, we investigate its efficacy in supporting the development of automatic Web page classification.}, acmid = {2609630}, added-at = {2016-01-18T23:36:37.000+0100}, address = {New York, NY, USA}, author = {Bing, Lidong and Guo, Rui and Lam, Wai and Niu, Zheng-Yu and Wang, Haifeng}, biburl = {https://www.bibsonomy.org/bibtex/2a94669026484ed98d3b92e5dd7e60de6/nosebrain}, booktitle = {Proceedings of the 37th International ACM SIGIR Conference on Research \&\#38; Development in Information Retrieval}, description = {Web page segmentation with structured prediction and its application in web page classification}, doi = {10.1145/2600428.2609630}, interhash = {29b12aa71341250eba417b4f2b1fdefe}, intrahash = {a94669026484ed98d3b92e5dd7e60de6}, isbn = {978-1-4503-2257-7}, keywords = {classification page prediction segmentation structured web}, location = {Gold Coast, Queensland, Australia}, numpages = {10}, pages = {767--776}, publisher = {ACM}, series = {SIGIR '14}, timestamp = {2016-01-18T23:36:37.000+0100}, title = {Web Page Segmentation with Structured Prediction and Its Application in Web Page Classification}, url = {http://doi.acm.org/10.1145/2600428.2609630}, year = 2014 }