SRDF: A Novel Lexical Knowledge Graph for Whole Sentence Knowledge Extraction.

In this paper, we present a novel lexical knowledge graph called SRDF and describe an extraction system that automatically generates a SRDF graph from the Korean natural language sentence. In the semantic web, knowledge is expressed in the RDF triple form but natural language sentences consist of multiple relationships between the predicates and arguments. For this reason, we design a SRDF graph structure that combines open information extraction method with reification for the whole sentence knowledge extraction. In addition, to add semantics to a SRDF graph, we establish a link between the lexical argument and entity in ontological knowledge base using the Entity Linking system. The proposed knowledge graph is adaptable for many existing semantic web applications. We present the results of an experimental evaluation and demonstrate the use of SRDF graph in developing a Korean SPARQL template generation module in the OKBQA platform.