Information Extraction from Free-Text Business Documents

Abstract

The objective of this chapter is an investigation of the applicability of information extraction techniques in real-world business applications dealing with textual data since business relevant data is mainly transmitted through free-text documents. In particular, we give an overview of the information extraction task, designing information extraction systems and some examples of existing information extraction systems applied in the financial, insurance and legal domains. Furthermore, we demonstrate the enormous indexing potential of lightweight linguistic text processing techniques applied in information extraction systems and other closely related fields of information technology which concern processing vast amounts of textual data.