Workshop: “Natural Language Processing Meets Holocaust Archives”

Language is central to the study of the Holocaust. The documentation of the genocide of Jews and Roma, building on war-time clandestine efforts, has grown since the liberation and today includes large corpora of testimonies, trial proceedings, letters and diaries, government documents, files of aid organisations and much more. The rich textual resources accumulated by Holocaust archives translate into an increasing amount of research data which can be analysed with natural language processing techniques. At the same time, the transnational character of the Holocaust, the fragmentation of its archival record, as well as its multilinguality offer both opportunities and challenges in the application of computational linguistics.

This interactive, hands-on workshop is a cooperation between two transnational European research infrastructures, bringing language technology together with Holocaust archives and data. The Common Language Resources and Technology Infrastructure (CLARIN) develops and supports state-of-the-art language tools and datasets as well as expertise on language technologies. The European Holocaust Research Infrastructure (EHRI) provides access to information about dispersed Holocaust archives and supports the Holocaust research community. Both infrastructures aim to empower researchers who tackle the challenges of the digital turn in the humanities and social sciences. Since the Czech node of EHRI is a part of the broader LINDAT/CLARIAH-CZ research infrastructure, Prague is a natural venue for discussing connections and cooperations.

The language of the workshop will be English. Research involving the multiple languages of Holocaust testimonies and documentation is encouraged and will be a central pillar of the workshop.

Participation will be by invitation only. Information on the CLARIN website about the event and registration can be found here.