Webpage understanding: beyond page-level search

In this paper we introduce the webpage understanding problem which consists of three subtasks: webpage segmentation, webpage structure labeling, and webpage text segmentation and labeling. The problem is motivated by the search applications we have been working on including Microsoft Academic Search, Windows Live Product Search and Renlifang Entity Relationship Search. We believe that integrated webpage understanding will be an important direction for future research in Web mining.

• Type: Conference
• Year: 2008
• Where: SIGMOD
• Authors: Zaiqing Nie, Ji-Rong Wen, Wei-Ying Ma
• Keywords: Database, SIGMOD 2008, Webpage Structure Labeling, Webpage Text Segmentation, Webpage Understanding Problem