Evaluating Deep Learning Methods for Word Segmentation of Scripta Continua Texts in Old French and Latin
Introduction: Thibault Clérice reports on the successfulness of recognizing word boundaries in scripta continua (typically late classic and early medieval Latin). This will not be easy reading for many a philologist and classicist, but it is well worth trying to bridge the gap. Next to explaining and evaluating Thibault Clérice releases the software Boudams used for his research.
[Click ‘Read more’ for the full post!]