ScienceTreks: an autonomous digital library system

The support for automation of the annotation process of large corpora of digital content is crucial for the success of semanticaware services in the digital library domain. In this paper we first present and discuss an information extraction pipeline from digital document acquisition to information extraction, processing and management. Such information pipeline is divided in a number of operational steps. The realization of these steps in an unsupervised information system enables us to introduce the concept of an Autonomous Digital Library system. In the following, we describe in some detail a first prototype: the ScienceTreks system. The proposed Autonomous Digital Library system can be used in automating end-toend information retrieval and processing, supporting the control and elimination of error-prone human intervention in the process.