NEH-Project History

We will facilitate the professional training of 21st century humanities scholars by making these manuscripts accessible to a broader community of researchers without requiring extensive and expensive paleography training.

This project originated in mid-2018 when Co-PIs Grieco and Rao became aware that their combined skills could solve the current problems of access and data mining concerning seventeenth century Spanish American notarial scripts. In 2019, with a start-up grant from UMKC’s Missouri Institute for Energy and Defense (MIDE), co-PIs Grieco and Rao recruited Ms. Alrasheed as their GRA for creating the first dataset and conducting experiments for Spanish character recognition. Simultaneously, Prof. Grieco built our interdisciplinary and international research team of historians with ample experience in notary records, Spanish paleography experts, and big data and knowledge management engineers. Internal funding from UMKC allowed us to advance this project and recruit new members into our team.

Presentations and Media Appearances

October, 2022. KGSAR: A Knowledge Graph-Based Tool for Managing Spanish Colonial Notary Records. Demo presented at The 21st International Semantic Web Conference (ISWC2022). Access the video and webpage for this demo.

October, 2022. Researchers Using Machine Learning to Transcript Centuries Old Scripts.

August, 2022. The City of Kansas City, MO Recognizes Our Research Team and the Support of the National Endowment for the Humanities.

February, 2022. Researchers Use Machine Learning to Decipher 17th Century Handwriting

August, 2020. Mizzou Engineer Using Machine Learning to Translate Historical Script

Presentation at the National Archives in Argentina

University of Missouri System Undergraduate Research Day at the Capitol 2021

Presentation at the Conversatorio de la Red de Archivos del CONICET - 12/11/2021