@inproceedings{1114,
  abstract     = {{This paper presents a system that uses the domain name of a German business website to locate its information pages (e.g. company profile, contact page, imprint) and then identifies business specific information. We therefore concentrate on the extraction of characteristic vocabulary like company names, addresses, contact details, CEOs, etc.  Above all, we interpret the HTML structure of documents and analyze some contextual facts to transform the unstructured web pages into structured forms. Our approach is quite robust in variability of the DOM, upgradeable and keeps data up-to-date. The evaluation experiments show high efficiency of information access to the generated data.  Hence, the developed technique is adaptive to non-German websites with slight language-specific modifications, and experimental results on real-life websites confirm the feasibility of the approach.}},
  author       = {{Lee, Yeong Su and Geierhos, Michaela}},
  booktitle    = {{Proceedings of the 9th Dutch-Belgian Information Retrieval Workshop}},
  editor       = {{Aly, Robin and Hauff, C. and Hiemstra, Djoerd and Huibers, Theo W.C. and de Jong, Franciska M.G.}},
  issn         = {{0929-0672}},
  keywords     = {{company search, information extraction, sublanguage}},
  location     = {{Enschede, The Netherlands}},
  pages        = {{79--86}},
  publisher    = {{Centre for Telematics and Information Technology (CTIT), University of Twente}},
  title        = {{{Business Specific Online Information Extraction from German Websites}}},
  year         = {{2009}},
}