Dynamic Integration and Visualization of Information from Multiple Evidence Sources


Type Research Project

Funding Bodies
  • Austrian Research Promotion Agency

Duration July 1, 2011 - June 23, 2013

http://www.weblyzard.com/divine/
  • Applied Information Technology AE (Details)
  • Information Business IN (Details)
  • Research Institute for Computational Methods FI (Details)

Tags

Press 'enter' for creating the tag
  • Belk, Stefan (Former researcher)
  • Föls, Michael (Former researcher)
  • Hornik, Kurt (Details) Project Head
  • Panny, Wolfgang (Details) Project Head
  • Rafelsberger, Walter (Former researcher)
  • Syed, Kamran Ali Ahmad (Former researcher)
  • Wohlgenannt, Gerhard (Former researcher) Project Head
 

Abstract (English)

Content providers and analysts alike increasingly rely on combining multiple data sources to build comprehensive, up-to-date and properly interlinked information spaces. These organizations criticallydepend on technologies for integrating these sources and tracking their evolution. DIVINE aims to provide such technologies, with a lightweight seed ontology acting as the focal point for integrating new evidence derived from multiple, evolving data sources. As such, the project advances ontology evolution research characterized by single-source solutions, which exploit mostly textual and rather static data. DIVINE integrates structured, unstructured and social sources. A modu-
lar and scalable portfolio of evidence acquisition services crawls public Web documents, queries Linked Open Data repositories, aggregates resource annotations from Web 2.0 applications, and triggers validation processes for missing or conflicting evidence. Since evidence from third-party sources is inherently uncertain, source-specific transformation rules and impact factors assign a confidence value to each new fact. A spreading activation network utilizes the collected evidence in conjunction with the confidence values for extending the seed ontology.

DIVINE will monitor domain changes over time to derive knowledge evolution patterns. This domain-centric view makes DIVINE novel among existing change detection approaches, which tend to be domain-agnostic. Each ontology element is assigned a confidence matrix, which records the changes in confidence values over time. Data services and dynamic visualizations reveal rising, declining or cyclic patterns in the confidence matrices. Such patterns are important indicators - the rate of change or the date of a concept's first appearance, for example, shed light on the evolution of knowledge and on the underlying processes that drive this evolution.

Partners

  • Gentics - Austria
  • webLyzard gmbh - Austria

Publications

Journal article

2012 Wohlgenannt, Gerhard and Weichselbraun, Albert and Scharl, Arno and Sabou, Marta. 2012. Dynamic Integration of Multiple Evidence Sources for Ontology Learning. Journal of Information and Data Management 3 (3), 243-254. (Details)

Contribution to conference proceedings

2013 Wohlgenannt, Gerhard, Belk, Stefan, Schett, Matthias. 2013. Computing Semantic Association: Comparing Spreading Activation and Spectral Association for Ontology Learning. In Computing Semantic Association: Comparing Spreading Activation and Spectral Association for Ontology Learning, Hrsg. Ramanna, S., Lingras, P., Sombattheera, C., Krishna, A. (eds.), MIWAI, Lecture Notes in Computer Science (LNCS) 8271, 317-328. Krabi, Thailand: Springer. open access (Details)
  Wohlgenannt, Gerhard, Belk, Stefan, Schett, Matthias. 2013. A Prototype for Automating Ontology Learning and Ontology Evolution. In 5th International Conference on Knowledge Engineering and Ontology Development (KEOD-2013), Hrsg. Joaquim Filipe and Jan Dietz, 407-412. Vilamoura, Portugal: SciTePress. open access (Details)
2012 Wohlgenannt, Gerhard, Weichselbraun, Albert, Scharl, Arno, Sabou, Marta. 2012. Confidence Management for Learning Ontologies from Dynamic Web Sources. In 4th International Conference on Knowledge Engineering and Ontology Development (KEOD-2012), Hrsg. Joaquim Filipe and Jan Dietz, 172-177. Barcelona, Spain: SciTePress. (Details)
  Lang, Heinz-Peter, Wohlgenannt, Gerhard, Weichselbraun, Albert. 2012. TextSweeper - A System for Content Extraction and Overview Page Detection. In Proceedings of the 2012 International Conference on Information Resources Management (Conf-IRM), Hrsg. Roman Brandtweiner, Lech Janczewski, 17-22. Vienna, Austria: AIS. (Details)
  Scharl, Arno and Alexander, Hubmann-Haidvogel and Weichselbraun, Albert and Wohlgenannt, Gerhard and Lang, Heinz-Peter and Sabou, Marta. 2012. Extraction and Interactive Exploration of Knowledge from Aggregated News and Social Media Content. In ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS-2012), Hrsg. J. C. Campos, S. D. J. Barbosa, P. Palanque, R. Kazman, M. Harrison and S. Reeves, 163-168. Copenhagen, Denmark: ACM Press. (Details)

Paper presented at an academic conference or symposium

2013 Wohlgenannt, Gerhard. 2013. A Prototype for Automating Ontology Learning and Ontology Evolution. 5th International Conference on Knowledge Engineering and Ontology Development (KEOD 2013), Vilamoura, Portugal, 19.09.-22.09. (Details)
  Wohlgenannt, Gerhard. 2013. Computing Semantic Association: Comparing Spreading Activation and Spectral Association for Ontology Learning. The 7th Multi-Disciplinary International Workshop on Artificial Intelligence (MIWAI2013), Krabi, Thailand, 09.12.2013-11.12.2013. (Details)
2012 Lang, Heinz-Peter, Wohlgenannt, Gerhard, Weichselbraun, Albert. 2012. TextSweeper - A System for Content Extraction and Overview Page Detection. Proceedings of the 2012 International Conference on Information Resources Management (Conf-IRM), Vienna, Österreich, 21.05-23.05. (Details)
  Wohlgenannt, Gerhard. 2012. Dynamic Integration and Optimization of Evidence Sources in Ontology Learning. An Informal Workshop on Text Analytics, Perth, Australien, 17.02-17.02.. Invited Talk (Details)

Classification

  • 1108 Informatics (Details)
  • 1109 Information and data processing (Details)

Expertise

  • Sematic Technologies, Natural Language Processing, Ontology Learning