07 May 2013
Improved access to newspapers: The Europeana Newspapers Project
Image source: National Library of Estonia
This is a brief post to highlight the activities of The Europeana Newspapers Project (ENP), a network of 18 partners (and 11 associated partners) working together to make more than 18 million digitised newspaper pages (including 10 million pages of full-text content) available via the Europeana ecosystem of online services, with aggregation carried out by The European Library.
The project will improve discoverability of content through the application of refinement methods for Optical Character Recognition (OCR), Optical Layout Recognition (OLR), named Entity Recognition (NER) and Page Class Recognition. It also addresses the challenges around quality evaluation for automatic refinement technologies, transformation of local metadata to the Europeana Data Model (EDM), and metadata standardisation in close collaboration with stakeholders from the public and private sector.
Demonstrations of the evaluation tools, OLR, NER tagging and the role of ground truth will take place at ENP first dissemination workshop on refinement and quality assessment at the University Library Svetozar Markovic, Belgrade, 13-14 June.
The British Library is a networking partner in the ENP and will be hosting an information day and a dissemination workshop in 2014.
For further information about the project, visit its website http://bit.ly/17WNlir and follow Europeana Newspapers on Facebook and @eurnews on Twitter.