Semantic Partitioner: Transformation of HTML Pages into
Semi-structured XML Documents


Abstract:

World Wide Web is transforming itself into the largest information resource making the process of information extraction (IE) from Web an important and challenging problem. In this paper, we present an automated IE system that is domain independent and that can automatically transform a given Web page into a semi-structured hierarchical document using presentation regularities. The resulting documents are weakly annotated in the sense that they might contain many incorrect annotations and missing labels. We also describe how to improve the quality of weakly annotated data by using domain knowledge in terms of a statistical domain model. We demonstrate that such system can recover from ambiguities in the presentation and boost the overall accuracy of a base information extractor by up to 20%. Our experimental evaluations with TAP data, computer science department Web sites, and RoadRunner document sets indicate that our algorithms can scale up to very large data sets.

Demo:


 

Skip Navigation Links.


Publications:

Conceptual Papers:

  • Srinivas Vadrevu, Fatih Gelgi, Hasan Davulcu. Semantic Partitioning Web Pages. (Accepted for Publication) In World Wide Web Journal: Internet and Information Systems, 2006.
  • Srinivas Vadrevu, Fatih Gelgi, Hasan Davulcu. Semantic Partitioning Web Pages. In The 6th International Conference on Web Information Systems Engineering (WISE), New York City, NY, November 2005. (Acceptance Rate: 12%)

Applications of Semantic Partitioner: