DEQA: deep web extraction for question answering

  • Authors:

  • Jens Lehmann;Tim Furche;Giovanni Grasso;Axel-Cyrille Ngonga Ngomo;Christian Schallhart;Andrew Sellers;Christina Unger;Lorenz Bühmann;Daniel Gerber;Konrad Höffner;David Liu;Sören Auer

  • Affiliations:

  • Department of Computer Science, Oxford University, Oxford, UK,Institute of Computer Science, University of Leipzig, Leipzig, Germany;Department of Computer Science, Oxford University, Oxford, UK;Department of Computer Science, Oxford University, Oxford, UK;Institute of Computer Science, University of Leipzig, Leipzig, Germany;Department of Computer Science, Oxford University, Oxford, UK;Department of Computer Science, Oxford University, Oxford, UK;CITEC, Bielefeld University, Bielefeld, Germany;Institute of Computer Science, University of Leipzig, Leipzig, Germany;Institute of Computer Science, University of Leipzig, Leipzig, Germany;Institute of Computer Science, University of Leipzig, Leipzig, Germany;Department of Computer Science, Oxford University, Oxford, UK;Institute of Computer Science, University of Leipzig, Leipzig, Germany

  • Venue:
  • ISWC'12 Proceedings of the 11th international conference on The Semantic Web - Volume Part II
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Despite decades of effort, intelligent object search remains elusive. Neither search engine nor semantic web technologies alone have managed to provide usable systems for simple questions such as "find me a flat with a garden and more than two bedrooms near a supermarket." We introduce deqa, a conceptual framework that achieves this elusive goal through combining state-of-the-art semantic technologies with effective data extraction. To that end, we apply deqa, to the UK real estate domain and show that it can answer a significant percentage of such questions correctly. deqa achieves this by mapping natural language questions to Sparql patterns. These patterns are then evaluated on an RDF database of current real estate offers. The offers are obtained using OXPath, a state-of-the-art data extraction system, on the major agencies in the Oxford area and linked through Limes to background knowledge such as the location of supermarkets.