Converting Textual Documents to RDF Triples, Covering Syntactic and Semantic Structures
Kimia Hassanzadeh · ERA: Education and Research Archive (University of Alberta) · 2013
An important contribution of the Semantic Web is a new format of data representation called Resource Description Framework (RDF). In RDF every piece of information is represented by a triple: . RDFs are densely interlinked between each other and are becoming very popular format of representing data on the web. As of August 2011, the last available data, more than 31 billion of triples exist on the web. In this set of work, we propose a system for information extraction from plain text in form of RDF triples. The proposed method is independent of prior knowledge-base and domain-specific patterns, and is applicable to any textual resources. Our approach is capable of identifying grammatical structure of an input sentence and analyzing its semantic to generate meaningful RDF triples of information, readable by human users and software agents. Through several experiments, we evaluate this approach by demonstrating the quality of our results.