Project 'A Gateway to European Newspapers online' started
Newspapers form an important part of library collections and are interesting to a large audience, which is why many libraries are currently digitizing their newspaper material. Despite these efforts, access to these collections is still erratic and often limited to local access points. In addition, the OCR (Optical Character Recognition) results are often unsatisfactory and there are problems with metadata and segmentation.
A group of 17 European partner institutions have recently joined forces in the project A Gateway to European Newspapers online to work on solving these problems at a European level and providing better access to these newspaper collections. More than 10 million newspaper pages will be added to the Europeana service.
European Newspapers is funded by the European Commission as an ICT-PSP project, Best Practice Network. This means that the project will work on the practical application of tools and services developed in other projects, such as several applications that have been developed in IMPACT.
The project aims at the aggregation and refinement of newspapers forThe European Library and Europeana and will address challenges particularly linked with digitized newspapers:
use of refinement methods for OCR, OLR/article segmentation, and named entity recognition (NER), and page class recognition to enhance search and presentation functionalities for Europeana customers;
quality evaluation for automatic refinement technologies;
transformation of local metadata to the Europeana Data Model (EDM);
metadata standardization in close collaboration with stakeholders from the public and private sector.
Each library participating in the project will distribute digitized newspapers and full-texts free of any legal restrictions to Europeana. There will be a special focus on newspapers published during the First World War, thus providing a meaningful addition to the resources aggregated by the current Europeana Collections 1914-1918.
European Newspapers has started on 1st February 2012 and will run for three years. The kick-off meeting of all partners of the project will take place on 1-2 March 2012 in Berlin, hosted by the project leader - The Berlin State Library.
The KB National Library of the Netherlands leads the work package ‘Refinement of digitized newspapers’, while The European Library is responsible for the work package ‘Aggregation and presentation of digitized newspapers for Europeana’. Part of the historic newspaper collection of the KB will also become available in Europeana at article level.
Staatsbibliothek zu Berlin (coördinator)
Koninklijke Bibliotheek & The European Library (TEL)