The widespread use of the PDF format for exchanging print-oriented documents raises new challenges in the research field of information extraction. In this paper we present a novel wrapper generation system for extracting information from PDF documents. Objects in a PDF document are accessible by their position, thus we exploit spatial constraints for driving the extraction of relevant information according to a set of group type definitions. Moreover, using fuzzy logic based conditions enables effectively handling uncertainty on the comprehension of the layout structure of PDF documents. The experimental results shown in the paper state a good accuracy of our PDF wrapping system.
A Wrapper Generation System for PDF Documents
Fazzinga Bettina;
2008
Abstract
The widespread use of the PDF format for exchanging print-oriented documents raises new challenges in the research field of information extraction. In this paper we present a novel wrapper generation system for extracting information from PDF documents. Objects in a PDF document are accessible by their position, thus we exploit spatial constraints for driving the extraction of relevant information according to a set of group type definitions. Moreover, using fuzzy logic based conditions enables effectively handling uncertainty on the comprehension of the layout structure of PDF documents. The experimental results shown in the paper state a good accuracy of our PDF wrapping system.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
