Bernhard Pollak, Record Detection on the Visual Layer; The REDEVILA System Master's Thesis, Vienna University of Technology, December 2007 (slightly corrected version, english front cover, hyperlinks)
[thesis]  [presentation]  [poster
Wolfgang Gatterbauer, Paul Bohunsky, Marcus Herzog, Bernhard Krüpl, Bernhard Pollak, Domain Independent Information Extraction from Web Tables, In Proceedings of the 16th International World Wide Web Conference (WWW 2007) pp. 71-80, Banff, Canada, May 2007. ACM Press.
[paper]  [project page]
Bernhard Pollak, Wolfgang Gatterbauer. Creating Permanent Test Collections of Web Pages for Information Extraction Research , In Proceedings of SOFSEM 2007: Theory and Practice of Computer Science, Volume II ICS AS CR, Prague, 2007, pp. 103-115. ISBN: 80-903298-9-6.
[paper]  [presentation]  [poster]  [project page]