Dynamic Integration of Multiple Evidence Sources for Ontology Learning

  • Gerhard Wohlgenannt Vienna University of Economics and Business, Institute for Information Business
  • Albert Weichselbraun University of Applied Sciences Chur, Faculty of Information Science
  • Arno Scharl MODUL University Vienna, Department of New Media Technology
  • Marta Sabou MODUL University Vienna, Department of New Media Technology
Keywords: Evidence Integration, Games with a Purpose, Knowledge Evolution, Ontology Learning

Abstract

Although ontologies are central to the Semantic Web, current ontology learning methods primarily make use of a single evidence source and are agnostic in their internal representations to the evolution of ontology knowledge. This article presents a continuous ontology learning framework that overcomes these shortcomings by integrating evidence from multiple, heterogeneous sources (unstructured, structured, social) in a consistent model, and by providing mechanisms for the fine-grained tracing of the evolution of domain ontologies. The presented framework supports a tight integration of human and machine computation. Crowdsourcing in the tradition of games with a purpose performs the evaluation of the learned ontologies and facilitates the automatic optimization of learning algorithms.

Author Biographies

Arno Scharl, MODUL University Vienna, Department of New Media Technology
Prof. Arno Scharl heads the Department of New Media Technology at MODUL University Vienna [1] and is the Managing Director of webLyzard technology gmbh [2]. Prior to his current appointments, he held professorships at the University of Western Australia and Graz University of Technology, was a Key Researcher at the Austrian Competence Center for Knowledge Management, and a Visiting Fellow at Curtin University of Technology and the University of California at Berkeley. Prof. Scharl completed his doctoral research and habilitation at the Vienna University of Economics and Business. Additionally, he holds a PhD from the University of Vienna, Department of Sports Physiology. He has been project leader of a number of award-winning semantic systems projects including IDIOM (www.idiom.at), RAVEN (www.modul.ac.at/nmt/raven) and Triple-C (www.ecoresearch.net/triple-c), author of more than 140 refereed publications, and editor of two books in Springer‘s Advanced Information and Knowledge Processing Series (The Geospatial Web, Environmental Online Communication). His current research interests focus on media monitoring and Web intelligence, human-computer interaction, and the integration of semantic and geospatial Web technology.

[1] www.modul.ac.at/nmt
[2] www.weblyzard.com
Marta Sabou, MODUL University Vienna, Department of New Media Technology
Dr Marta Sabou is an Assistant Professor at the Department of New Media Technology as of May 2010, currently focusing on the following research themes: the use of human computation technologies for acquiring linguistic and factual knowledge (uComp project, to start in Nov'12) and the use of linked open data to support decision support in the tourism and climate change domains (DIVINE project). Before joining MODUL University Vienna, she was a Research Fellow at the Knowledge Media Institute (KMi) of the Open University, UK, where she worked on building novel applications that are capable of exploring large-scale, semantic Web content, including the development of methods for ontology selection, modularization and matching. She holds a Master's Degree in Artificial Intelligence from the Vrije Universiteit, Amsterdam. In 2005 she completed her PhD at the Knowledge Representation Group of the Vrije Universiteit on the topic of enhancing and (semi)automatically learning ontologies used to specify the semantic description of Web services. In 2006, she won IEEE Intelligent System’s Ten to Watch Award. Much of her work was carried out in the context of major European research projects, such as WonderWeb, KnowledgeWeb, SWAP, NeOn, OpenKnowledge and SmartProducts.  Her work has been published in IEEE Intelligent Systems, Journal of Web Semantics, and high-impact conferences such as the International World Wide Web Conference and the International Semantic Web Conference.
Published
2012-09-27
Section
SBBD Articles