AI in Historical Analysis
Taylor discusses using AI and machine learning to automate the process of identifying damaged glyphs in historical documents to determine their printer origin. The project aims to scale the reasoning process used by historians manually and apply it to a vast collection of early modern documents. The approach involves character box identification, unsupervised OCR, and graph clustering to assign printer attribution across the collection.In this clip
From this podcast
NLP Highlights
97 - Automated Analysis Of Historical Printed Documents, With Taylor Berg-Kirkpatrick
Related Questions