Machine Learning and the Future of Philology: A Case Study

This paper argues that machine learning (ML) has a role to play in the future of philology, understood here as a discipline concerned with preserving and elucidating the global archive of premodern texts. We offer one initial case study in order to outline broader possibilities for the field. The argument is in four parts. First, we offer a brief introduction to the history of classical philology, focusing on the development of three technologies: writing, printing, and digitizing. We evaluate their impact and emphasize some elements of continuity in philological practice. Second, we describe Logion, an ML model we are currently developing to support various philological tasks, such as making conjectures to fill lacunae, identifying scribal errors, and proposing emendations. In part three, we present some of the results achieved to date in editing the work of the Byzantine author Michael Psellos. Finally, we build on the specific case study presented (part three), as well as our more general considerations on philology (part one) and ML (part two), in order to shed light on current challenges and future opportunities for the global archive of premodern texts.