We are very pleased to announce our latest project supported by the National Endowment for the Humanities, in the form of a new Stage III Digital Humanities Advancement Grant continuing the NEH's long-standing support of our work in Coptic Scriptorium. The new grant is titled:

A Linked Digital Environment for Coptic Studies: Integrating Heterogeneous Data with Machine Learning and Natural Language Processing

The focus of the grant, which is set to run from fall 2018 for three years, is developing more robust tools which can deliver high accuracy analyses with less manual intervention in the face of more heterogeneous data, including Coptic materials from OCR, spelling variation across editions and varying scholarly conventions. This will allow us to grow the collection of corpora made available over the project’s tools in the coming months and years. Additional areas of work include improving our work on Linked Open Data standards connecting the project to other initiatives in the field, and pioneering methods for automatic Named Entity Recognition in Coptic, among other things.