User driven information extraction with LODIE

Anna Lisa Gentile, Suvodeep Mazumdar · MADOC (University of Mannheim) · 2014

Abstract. Information Extraction (IE) is the technique for transform-ing unstructured or semi-structured data into structured representation that can be understood by machines. In this paper we use a user-driven Information Extraction technique to wrap entity-centric Web pages. The user can select concepts and properties of interest from available Linked Data. Given a number of websites containing pages about the concepts of interest, the method will exploit (i) recurrent structures in the Web pages and (ii) available knowledge in Linked data to extract the information of interest from the Web pages. 1

Read the paper · More papers on PaperTik