Advances in Information Extraction

Jakub Piskorski

In: Witold Abramowicz (Hrsg.). Knowledge-based Information Retrieval and Filtering from the Web. Kapitel 2 Seiten 23-52 Kluwer Academic Publishers 2003.


Nowadays, knowledge relevant to business of any kind is mainly transmitted through free-text documents. Latest trends in information technology such as Information Extraction (IE) provide dramatic improvements in conversion of the overflow of raw textual information into valuable and structured data. This chapter gives a comprehensive introduction to information extraction technology including design, processing natural language, and evaluation issues of IE systems. Further, we present a retrospective overview of IE systems which have been successfully applied in real-world business applications which deal with processing vast amount of textual data, and we discuss current trends. Finally, we demonstrate an enormous indexing potential of lightweight linguistic text processing techniques in other areas of information technology closely related to IE.

jp-Chapter02.pdf (pdf, 331 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence