Incorporating site-level knowledge to extract structured data from web forums Export

@inproceedings{citeulike:4387322, abstract = {Web forums have become an important data resource for many web applications, but extracting structured data from unstructured web forum pages is still a challenging task due to both complex page layout designs and unrestricted user created posts. In this paper, we study the problem of structured data extraction from various web forum sites. Our target is to find a solution as general as possible to extract structured data, such as post title, post author, post time, and post content from any forum site. In contrast to most existing information extraction methods, which only leverage the knowledge inside an individual page, we incorporate both page-level and site-level knowledge and employ Markov logic networks (MLNs) to effectively integrate all useful evidence by learning their importance automatically. Site-level knowledge includes (1) the linkages among different object pages, such as list pages and post pages, and (2) the interrelationships of pages belonging to the same object. The experimental results on 20 forums show a very encouraging information extraction performance, and demonstrate the ability of the proposed approach on various forums. We also show that the performance is limited if only page-level knowledge is used, while when incorporating the site-level knowledge both precision and recall can be significantly improved.}, address = {New York, NY, USA}, author = {Yang, Jiang M. and Cai, Rui and Wang, Yida and Zhu, Jun and Zhang, Lei and Ma, Wei Y.}, booktitle = {WWW '09: Proceedings of the 18th international conference on World wide web}, citeulike-article-id = {4387322}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1526709.1526735}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1526709.1526735}, comment = {[Talk] Exploit sitemap; cluster pages by layout. Find out where the author/title/date/etc. are in the DOM of a cluster of pages.}, doi = {10.1145/1526709.1526735}, isbn = {978-1-60558-487-4}, keywords = {text, xml}, location = {Madrid, Spain}, pages = {181--190}, posted-at = {2009-04-23 15:50:24}, priority = {0}, publisher = {ACM}, title = {Incorporating site-level knowledge to extract structured data from web forums}, url = {http://dx.doi.org/10.1145/1526709.1526735}, year = {2009} }

TY - CONF ID - citeulike:4387322 L3 - citeulike-article-id:4387322 N2 - Web forums have become an important data resource for many web applications, but extracting structured data from unstructured web forum pages is still a challenging task due to both complex page layout designs and unrestricted user created posts. In this paper, we study the problem of structured data extraction from various web forum sites. Our target is to find a solution as general as possible to extract structured data, such as post title, post author, post time, and post content from any forum site. In contrast to most existing information extraction methods, which only leverage the knowledge inside an individual page, we incorporate both page-level and site-level knowledge and employ Markov logic networks (MLNs) to effectively integrate all useful evidence by learning their importance automatically. Site-level knowledge includes (1) the linkages among different object pages, such as list pages and post pages, and (2) the interrelationships of pages belonging to the same object. The experimental results on 20 forums show a very encouraging information extraction performance, and demonstrate the ability of the proposed approach on various forums. We also show that the performance is limited if only page-level knowledge is used, while when incorporating the site-level knowledge both precision and recall can be significantly improved. CY - Madrid, Spain SN - 978-1-60558-487-4 AD - New York, NY, USA EP - 190 TI - Incorporating site-level knowledge to extract structured data from web forums PB - ACM T2 - WWW '09: Proceedings of the 18th international conference on World wide web SP - 181 KW - text KW - xml N1 - [Talk] Exploit sitemap; cluster pages by layout. Find out where the author/title/date/etc. are in the DOM of a cluster of pages. AU - Yang, Jiang AU - Cai, Rui AU - Wang, Yida AU - Zhu, Jun AU - Zhang, Lei AU - Ma, Wei PY - 2009/// UR - http://dx.doi.org/10.1145/1526709.1526735 ER -