@inproceedings{,
    author = {Lee, Yeong Su; Geierhos, Michaela},
    title = {Business Specific Online Information Extraction from German Websites},
    editor = {Aly, Robin; Hauff, Claudia; Hiemstra, Djoerd; Huibers, Theo W. C.; de Jong, Franciska M. G.},
    booktitle = {Proceedings of the 9th Dutch-Belgian Information Retrieval Workshop},
    series = {},
    journal = {},
    address = {Twente},
    publisher = {Centre for Telematics and Information Technology (CTIT), University of Twente},
    edition = {},
    year = {2009},
    isbn = {},
    volume = {},
    number =  {},
    pages = {79-86},
    url = {},
    doi = {},
    keywords = {company search ; information extraction ; sublanguage},
    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.},
    note = {},
    
    
    
}