In this paper we present a new approach to extract relevant information by knowledge graphs from natural language text. We give a multiple level model based on knowledge graphs for describing template information, and investigate the concept of partial structural parsing. Moreover, we point out that expansion of concepts plays an important role in thinking, so we study the expansion of knowledge graphs to use context information for reasoning and merging of templates.
|Name||Memorandum Faculteit TW|
|Publisher||University of Twente, Department of Applied Mathematics|