2000 character limit reached
Mining Semi-structured Data (1504.04031v1)
Published 15 Apr 2015 in cs.DB
Abstract: The need for discovering knowledge from XML documents according to both structure and content features has become challenging, due to the increase in application contexts for which handling both structure and content information in XML data is essential. So, the challenge is to find an hierarchical structure which ensure a combination of data levels and their representative structures. In this work, we will be based on the Formal Concept Analysis-based views to index and query both content and structure. We evaluate given structure in a querying process which allows the searching of user query answers.