Web Page Segmentation Towards Information Extraction for Web Semantics

Today, web is a large source of information which may be structured or unstructured. The need is efficient information extraction from various unstructured sources on the web. Therefore, information extraction is playing a prominent role in the current scenario. It focuses on automatically extracting structured information from unstructured distributed resources on the web and is based on several approaches. Web page segmentation is one of the most significant techniques where a web page is broken down into semantically related parts. There are various approaches to Web page segmentation. In this paper, the first information extraction has been explored, discussed and reviewed. Second, a revisit has been done on web page segmentation and its various approaches where a comparative analysis has been made. Third, various phases of vision-based web page segmentation have been presented and reviewed along with a flowchart. Finally, the results and conclusions have been presented along with the future work.