Towards interoperability: Introducing the Impresso data lab for the enrichment and analysis of historical media

The workshop explores the intersection of four developments improving interoperability between static infrastructures and dynamic research needs in Digital Humanities: the shift towards computational processing, large-scale NLP-based semantic enrichment of cultural heritage data, integration of LLMs in research workflows, and the development of "data labs" by cultural heritage institutions. The Impresso data lab aims to address limitations researchers face when dealing with diverse data and large-scale collections. It offers access to a growing Western European newspaper and radio corpus, complementing the Impresso web app with flexible computational analysis capabilities. The data lab provides API accessibility, supports dynamic research workflows, offers annotation services, and allows enrichment import. The workshop agenda includes introductions to the Impresso project, demonstrations of the web app and data lab capabilities, and hands-on sessions. It aims for active debate among participants about the prospects and real-world needs for interoperability between research infrastructures and research practices.