Intertext Matching in the Digital Humanities
Intertext matching is crucial for classics studies, in which authors routinely borrowed from or alluded to prior work. These matches are often difficult to find manually, requiring extensive knowledge of many texts potentially spanning multiple languages. The Tesserae project is an ongoing, multi-institution project funded by the National Endowment for the Humanities (NEH) that automates intertext matching.
Our contribution is a revamped version of the core Tesserae software using software engineering best practices to make in-browser intertexts matching more customizable and scalable than ever. Additionally, we are exploring applications of machine learning and new methods for scoring methods to enable intertext studies at large scale.
Jeff Kinnison, Walter Scheirer
Collaborators: Christopher Forstall
