Experimental working group working on generating transcriptions of archival documents using machine learning
Sponsored by the Vanderbilt Library Digital Scholarship and Communications Office
Students shared their favorite stories from the diary to this digital exhibit. We used the Omeka digital publishing platform, designed for cultural heritage institutions, and introduced students to Dublin Core metadata standard.
https://cursive.library.vanderbilt.edu/
All meetings will take place in the Center for Digital Humanities (Buttrick Hall 344) from 3:00 - 4:00.
Date | Title |
---|---|
January 13 | 1 - Introduction |
January 20 | NO CLASS - Martin Luther King Day |
January 27 | 2 - Scanning documents |
February 3 | 3 - ABBYY FineReader and Tesseract |
February 10 | 4 - Cleaning Results With RegEx |
February 17 | 5 - Introduction to Machine Learning and Neural Networks |
February 24 | NO CLASS |
March 2 | NO CLASS - Spring Break |
March 9 | NO CLASS |
March 16 | 6 - Transkribus |
March 23 | 7 - Ocropus |
March 30 | 8 - |
April 6 | 9 - Creating a digital exhibit |
April 12 | 10 - Wrap-up |
April 21 | Buchanan Fellows Reception (12:00 - 2:00 pm in Central Library) |