Home // SEMAPRO 2012, The Sixth International Conference on Advances in Semantic Processing // View article

Using DBPedia to Bootstrap new Linked Data

Authors:
Alexiei Dingli
Silvio Abela

Keywords: RDF; Linked Data; Semantic Web; XML

Abstract:
If the documents on the WWW were somehow structured, then machines can be made to extract meaning (or semantics) from the content and help us find more data that is relevant to what we search. There is an effort to find better ways to include machine-meaning in the documents already present on the WWW by using Natural Language Processing (NLP) techniques and Web technologies such as XML and RDF that are used to insert and represent the ``meaning" in the extracted content. We propose an application that uses Information Extraction to extract patterns from a human readable text and use it to try and find similar patterns elsewhere by searching the WWW. This is done to bootstrap the creation of further data elements. These data elements are then stored in RDF format and reused in other searches. Our evaluation show that this approach gives an encouraging degree of success with a precision of 79% and a recall of 71%.

Pages: 48 to 53

Copyright: Copyright (c) IARIA, 2012

Publication date: September 23, 2012

Published in: conference

ISSN: 2308-4510

ISBN: 978-1-61208-240-0

Location: Barcelona, Spain

Dates: from September 23, 2012 to September 28, 2012