Stephen Flynn, William Rial, and Sofia Visa (College of Wooster)
This presentation offers perspectives from the College of Wooster’s Computer Science and Library faculties on the development of a project that will ultimately result in digital editions of Madeleine de Scudéry’s series of seventeenth- and eighteenth-century _Conversations_. French Professor Laura Burch, after teaching from PDF copies of seventeenth-century books, noted that students had as many difficulties with the printed typography as with the antiquated French. A project developed in which students transcribed, but did not modernize, the text. Working with Emerging Technologies Librarian Stephen Flynn, who will speak for the project, this team produced a TEI-encoded copy of the first volume of _Conversations_, _Conversations Sur Divers Sujets_ (1680). Flynn will discuss the project’s workflow, which included a low-barrier version of XML that made encoding easier for the students while allowing for transformations into TEI once transcriptions were completed.
A partner project arose from this in which CS Professor Sofia Visa guided a research project by CS student Will Rial, both of whom will present on their experiences. Rial used Machine Learning and Optical Character Recognition (OCR) technologies to automate the transcription of the first volume of _Conversations_ as a pilot for processing the remaining four volumes. Rial will discuss his optimization of the workflows developed in the Early Modern OCR Project (eMOP), including dictionary creation and post-processing algorithms, and Visa will present on the pedagogical perspective of guiding such a project.