The Condorcet project was funded by the Dutch Technology Foundation (STW) through the Werkgemeenschap Informatiewetenschap. The project was carried out at the Vossius Laboratory of the University of Twente. The main objective of the Condorcet project was to design, build and evaluate a prototype automated indexing system, supporting Information Retrieval from large, reality-level volumes (tens of thousands) of documents. The prototype has been tested on some 400 documents from two scientific domains: mechanical properties of engineering ceramics as a field of engineering, and epilepsy as a subfield of medicine. The Condorcet system is concerned with semi-automatic indexing of documents, thus producing document representations, to be used in matching user requests to these representations. More specifically, the Condorcet system indexes scientific documents by mapping titles and abstracts (henceforth referred to as descriptions) of the documents to concepts and relations, defined in modern versions of classical indexing thesauri, i.e. ontologies. It does so by using three kinds of knowledge: domain knowledge, linguistic knowledge and indexing knowledge.
|Place of Publication||Enschede, the Netherlands|
|Publisher||Centre for Telematics and Information Technology (CTIT)|
|Publication status||Published - Jan 2000|
|Name||CTIT technical report series|
|Publisher||University of Twente, Centre for Telematics and Information Technology (CTIT)|
van Bakel, B. J., Boon, R. T., Mars, N., & Oltmans, J. A. (2000). Condorcet final report. (CTIT technical report series; No. TR-CTIT-00-02). Enschede, the Netherlands: Centre for Telematics and Information Technology (CTIT).