Ansund: Using Machine Learning to Develop a New, Exhaustive, Open Access Corpus of Old English: Pilot Findings

A conference organised by the Centre For The Book and the School of English. 

Old English (c. 600-1150) is the earliest phase of written English. At present, the standard electronic repository of Old English texts is incomplete and sits behind a paywall. This repository took almost 40 years to compile, but Handwritten Text Recognition (HTR), a new branch of machine learning, means it is possible a new, exhaustive corpus of Old English could be built quickly and affordably. This colloquium, funded by the Trinity Long Room Hub Research Incentive scheme, presents a pilot of this project, showing how it immeasurably enhances our ability to answer existing research questions, permits a raft of new ones, and is a significant step to making research on Old English more open. The morning session and lunch are open to all (9-1.30). 

Please register here whether attending in person or online.

Please indicate if you have any access requirements, such as ISL/English interpreting, so that we can facilitate you in attending this event. Contact: mark.faulkner@tcd.ie