BIS record '2007/1/450'

BibTeX

@inproceedings{BIS:2007/1/450,
  author        = {Radek Burget},
  title         = {Automatic Document Structure Detection for Data Integration},
  year          = {2007},
  session       = {Information Retrieval},
  pages         = {394--400},
  crossref      = {BIS:2007/1},
  bibsource     = {BIS, http://bis.kie.ue.poznan.pl/biblio/},
  abstract      = {A great amount of information is still being stored in loosely structured documents in several widely used formats. Due to the lack of data description in these documents, their integration to the existing information systems requires sophisticated pre-processing techniques to be developed. To the document reader, the content structure is mostly presented by visual means. Therefore, we propose a method for the discovery of the logical document structure based on the analysis of various visual properties of the document such as the page layout or text properties. This method is currently being tested and some promissing preliminary results are available.}
}

  
@proceedings{BIS:2007/1,
  editor        = {Witold Abramowicz},
  booktitle     = {Business Information Systems, 10th International Conference, BIS 2007, Poznań, Poland, April 2007},
  title         = {Business Information Systems, 10th International Conference, BIS 2007, Poznań, Poland, April 2007},
  publisher     = {Springer-Verlag},
  isbn          = {978-3-540-72034-8},
  year          = {2007},
  bibsource     = {BIS, http://bis.kie.ue.poznan.pl/biblio/}
}