ProgramArts & HumanitiesHybrid

Digitizing colonial-era archives with OCR and NLP

Aurora Polytechnic

About this program

A two-year master's program pairing historians with computational linguists to digitize, transcribe, and analyze colonial-era archives. Participants build multilingual OCR and NLP pipelines while engaging critically with the ethics of archival preservation. The program combines on-site archive work with remote collaboration and produces an openly accessible digital corpus.

What's included

Hands-on work with rare historical archives
Training in multilingual OCR and NLP pipelines
Contribution to an open-access digital corpus
Interdisciplinary mentorship across history and CS

Focus areas

Digital HumanitiesNLPHistory