Posted on Wednesday December 1, 2021

Updated on Wednesday December 1, 2021

OCCAM: a tool for OCR & Machine Translation for Europeana items

This session from Europeana 2021 explores the ‘OCCAM’ tool, which provides a workflow for making items on Europeana available in a machine-readable format (OCR).

About

Historical newspapers are a core resource for humanities research and are increasingly available online as digital images or PDFs. However, these formats don't allow you to search or access the full text of these materials. 

Watch this session to find out about the ‘OCCAM’ tool, which provides a workflow for making items on Europeana available in a machine-readable format (OCR) and then translating them. This session shows how OCCAM works to extend the (meta)data on Europeana’s OAI-PMH server. This data could then be published via OCCAM’s OAI-PMH server, which could be re-ingested to Europeana.

Speaker

Resources

  • Join the Europeana Network Association to receive news about the digital transformation of the cultural heritage sector, network with peers and hear about relevant events, resources and opportunities
top