@InProceedings{ GatterbauerBHKP2007:Towards,
author = {Wolfgang Gatterbauer and Paul Bohunsky and Marcus Herzog and Bernhard Kr\"{u}pl and Bernhard Pollak},
title = {Towards Domain-Independent Information Extraction from Web Tables},
year = {2007},
month = may # {~8--12,},
booktitle = {Proceedings of the 16th International {W}orld {W}ide {W}eb Conference ({WWW}~2007)},
pages = {71--80},
location = {Banff, Alberta, Canada},
publisher = {ACM Press},
isbn = {},
doi = {},
url = {http://www2007.org/paper790.php},
pdf = {http://www2007.org/papers/paper790.pdf},
abstract = {Traditionally, information extraction from web tables has
focused on small, more or less homogeneous corpora, often
based on assumptions about the use of
tags. A
multitude of different HTML implementations of web tables
make these approaches difficult to scale. In this paper, we
approach the problem of domain-independent information
extraction from web tables by shifting our attention from the
tree-based representation of web pages to a variation of the
two-dimensional visual box model used by web browsers to
display the information on the screen. The thereby obtained
topological and style information allows us to fill the gap
created by missing domain-specific knowledge about content
and table templates. We believe that, in a future step, this
approach can become the basis for a new way of large-scale
knowledge acquisition from the current “Visual Web.”},
keyword = {Information extraction, Web mining, Web tables, Web page representation, Visual analysis},
}