Europeana with user transcriptions and annotations

EnrichEuropeana developed tools and services for end users to crowdsource the enrichment of digital cultural heritage (CH) available through Europeana. The project run Citizen Science transcription and enrichment campaigns for CH collections in order to facilitate re-use of materials in education and research. Building on the technology and experience developed through the Europeana 1914-1918 Transcribathon, EnrichEuropeana aimed at expanding the potential of this technology and to make it available for other kinds of materials from different time periods and CH areas (e.g. arts, science, history). The newly-created resources were integrated with the original collections and made available for the public user in the portals of Europeana, aggregators and content providers.

The project produced a reliable data-exchange infrastructure with specialised interfaces for selection, import, enrichment and ingestion of data from and into European digital heritage collections. The exchange of data was developed using the public APIs offered by Europeana and other data providers (e.g. Polish Digital Libraries Federation, German Digital Library). The semantic enrichment of the transcribed text was achieved by incorporating natural language processing, named entity recognition and machine translation.

The endeavour promoted deeper engagement, understanding and access to European digital cultural heritage. To maximise public interest, EnrichEuropeana piloted an enrichment campaign using materials from the crowdsourced Europeana Collections such as: Europeana 1989, Europeana 1914-1918 or Migration in the Arts and Sciences.

Facts:

• Projektbeginn: September 2018
• Projektdauer: 18 Monate
• Budget: ca. xy EUR
• Förderung: EC CEF TC