@inproceedings{cha05,
  abstract = {We present an integrated framework for the document conversion from legacy formats to XML format. We describe the LegDoC project, aimed at automating the conversion of layout annotations layout-oriented formats like PDF, PS and HTML to semantic-oriented annotations. A toolkit of different components covers complementary techniques the logical document analysis and semantic annotations with the methods of machine learning. We use a real case conversion project as a driving example to exemplify different techniques implemented in the project.},
  added-at = {2009-01-14T00:43:43.000+0100},
  address = {Vienna, Austria},
  author = {Chanod, Jean-Pierre and Chidlovskii, Boris and D\'ejean, Herv\'e and Fambon, Olivier and Fuselier, J\'er\^ome and Jacquin, Thierry and Meunier, Jean-Luc},
  biburl = {http://www.bibsonomy.org/bibtex/2dc8f8e8078e4ee9552c95c682abca916/dret},
  booktitle = {Proceedings of the 9th European Conference on Digital Libraries},
  crossref = {ecdl2005},
  description = {dret'd bibliography},
  editor = {Rauber, Andreas and Christodoulakis, Stavros and {Min Tjoa}, A.},
  index = {ECDL 2005},
  interhash = {cc35878f613128decd4a7d92c1208869},
  intrahash = {dc8f8e8078e4ee9552c95c682abca916},
  keywords = {imported},
  month = {September},
  pages = {92-103},
  publisher = {Springer-Verlag},
  series = {Lecture Notes in Computer Science},
  timestamp = {2009-01-14T00:43:43.000+0100},
  title = {From Legacy Documents to XML: A Conversion Framework},
  uri = {http://www.springerlink.com/link.asp?id=5xnqptg4hrdqmy3g},
  volume = 3652,
  year = 2005
}