Talks and Poster Presentations (without Proceedings-Entry):
B. Krüpl-Sypien, R. Fayzrakhmanov, W. Holzinger, M. Panzenböck:
"A Versatile Model for Web Page Representation, Information Extraction and Content Re-Packaging";
Talk: The ACM Symposium on Document Engineering - DocEng,
Mountain View, California, USA;
On today's Web, designers take huge e orts to create visually rich websites that boast a magnitude of interactive elements. Contrarily, most web information extraction (WIE) algorithms are still based on attributed tree methods which struggle to deal with this complexity. In this paper, we introduce a versatile model to represent web documents. The model is based on gestalt theory principles|trying to capture the most important aspects in a formally exact way. It
(i) represents and uni es access to visual layout, content and functional aspects; (ii) is implemented with semantic web techniques that can be leveraged for i.e. automatic reasoning. Considering the visual appearance of a web page, we view it as a collection of gestalt gures|based on gestalt primitives|each representing a speci c design pattern, be it navigation menus or news articles. Based on this model, we introduce our WIE methodology, a re-engineering process
involving design patterns, statistical distributions and text content properties. The complete framework consists of the UOM model, which formalizes the mentioned components, and the MANM layer that hints on structure and serialization, providing document re-packaging foundations. Finally, we discuss how we have applied and evaluated our model in the area of web accessibility.
"Official" electronic version of the publication (accessed through its Digital Object Identifier - DOI)
Project Head Reinhard Pichler:
TASK MINING from CROWD BEHAVIOUR
Created from the Publication Database of the Vienna University of Technology.