The Flow – From Deep-Learning to Digital Analysis and their Role in the Humanities Creating, Evaluating, and Critiquing Workflows for Historical Corpora

Schema of the workflow

Advancement of digital methods in the work with historical manuscripts
Digitization is now an integral part of historical research. Historians and the humanities in general have much to gain from advances in Handwritten Text Recognition and Natural Language Processing. However, the tools and workflows to make use of new technologies are often only available to those who have a deep understanding of information science and coding abilities. To address this issue, the project “The Flow” will develop more standardized digital workflows based on existing technology, making it easier for researchers to work with historical sources digitally.

Four subprojects will contribute to that goal by analysing legal and administrative sources from England, the northern European Hanse area, Switzerland, and Ethiopia. The sources will be studied with digital methods, namely the creation and application of Handwritten Text Recognition and Natural Language Processing models for historical languages. Through such semi-automated processes and workflows established in the project, historians will be able to study longer time periods and gain a deeper understanding of the legal practices and social life of the communities in question.