eLabs Events
- This event has passed.
Unlocking the U.S. Department of State’s “Consular Cards”: Experimenting with AI Transcription of Handwritten Historical Documents (A Webinar with FromThePage)
July 25, 2024 12:00 pm – 1:00 pm Eastern Daylight Time
Do today’s latest “AI” models offer capabilities not possible with traditional OCR, for unlocking documents whose handwritten contexts were impenetrable with previous technologies? A decade ago, the Office of the Historian scanned its “Consular Cards file”, a collection of 6,500 handwritten index cards containing listings of officials at all U.S. diplomatic and consular posts from 1789-1960. A unique and foundational source for understanding the history of U.S. foreign relations, the utility of the scanned cards remained limited due to OCR’s inability to extract text from the ornate cursive handwriting on these cards. Experiments conducted this year with multimodal AI tools have produced breakthrough, if imperfect, results. The talk will demonstrate the methodology and results of these experiments and will offer tips and caveats for scholars considering such tools.
The webinar, which is hosted by FromThePage, will be held on July 25, 2024 at 12:00 PM EDT / 11:00 AM CDT / 9:00 AM PDT. Signing up will send you an invitation with the details and a follow up with the recording.
About the Speaker
Joseph C. Wicentowski is the Digital History Advisor at the Office of the Historian, Foreign Service Institute, U.S. Department of State. After completing his Ph.D. in modern Chinese history at Harvard University in 2007, he joined the Office of the Historian and led the project to digitize the Foreign Relations of the United States(FRUS) series—a 160 year-old documentary edition comprising over 550 volumes and 300,000 documents—and make it and other historical publications and datasets available as open access publications on the Office’s public website, history.state.gov, and via open government data repositories on github.com/HistoryAtState. With Clifford Anderson, he co-authored XQuery for Humanists (Texas A&M University Press, 2020), a book that emerged from his experience learning XQuery to build scholarly interfaces to historical texts and teaching the language to others.
