Semantic enrichment on Large Corpora: a case study for Patrologia Graeca

Semantic enrichment on Large Corpora: a case study for Patrologia Graeca

In this paper a case study for Patrologia Graeca (PG) is presented to reveal the difficulties that arise when a semantic enrichment though interconnections is pursued with specific aim to discuss an alternative cooperative architecture between libraries. The presented case method interconnects the PG with a range of satellite scanned or editable texts to provide a better user navigation experience, easy citation for specific PG page and document interconnections. Although the semantic enrichment can be achieved by using semi-manual methods, this is not recommended due to the fact that these tasks are time consuming and costly. Therefore a new architecture for a better cooperation between libraries and cultural institutions is proposed in order to provide a framework for the application of Artificial Intelligence(AI) and Pattern recognition (PR) techniques for mass enrichment on Large corpora. The proposed framework creates the possibility for the participating libraries to cooperate and provide a high quality commonly accepted version of a specific corpus which is used by independent research teams to apply AI and PR methods and create automatically the structure and the interconnections between documents.