The READ project is working to make handwritten historical collections more accessible through the development and application of Handwritten Text Recognition (HTR) technology. This technology is certainly of interest to archivists and scholars but we hope that members of the public will find it useful too! The crowdsourcing initiative Transcribe Bentham is already part of the READ project and we will be creating a new open source crowdsourcing platform which can be used and adapted by any institution which would like to get volunteers to work on a manuscript collection. We have also begun working with a small focus group of volunteers to introduce them to the Transkribus transcription platform and the possibilities of HTR technology. Barbara Denicolo is working with the Civic Archives of Bozen-Bolzano (one of the READ MOU partners) to manage this project and she gives a summary below of her progress so far:
‘‘Transcribing the Bozner Ratsprotokolle’ is a collaboration between READ and the Civic Archives of Bozen-Bolzano, Italy, which was set up at the beginning of 2016. Our aim is to recruit and train volunteers to work with Transkribus to transcribe the ‘Bozner Ratsprotokolle’; records of the municipal council of the town which were written between the fifteenth and nineteenth centuries. These transcripts will help to train a HTR engine to read the ‘Bozner Ratsprotokolle’ collection. Once a computer is capable of processing these documents, users will be able to view automatically-generated transcripts and search for particular keywords that they might be interested in. The archive could also use these transcripts to create an enriched digital edition of the collection.
Page from the Ratsprotokoll (1600) [Image from Civic Archives of Bozen-Bolzano]
Before I asked any volunteers to work with Transkribus, I needed to learn how to use it myself! I am familiar with the process of transcribing historical documents. I have studied medieval history for many years, worked with sources in various archives and am about to start my PhD. I managed to transcribe 60 pages from the ‘Bozner Ratsprotokolle’ collection, which is a strong basis for training the HTR. The next step was to recruit some volunteers who could help us to produce even more training data.
Between May and September 2016 we sent out a call for volunteers using the archives’ website, flyers, emails and word of mouth. An advert placed in a local newspaper seems to have attracted quite a few participants, whilst Facebook posts helped me to get in contact with several students.
We now have a group of around 30 interested people, about half of whom have started to work with Transkribus. My experience so far suggests that it is difficult to find an ideal volunteer – older people generally have time to participate and are skilled in reading old handwriting but need more support to understand and work with Transkribus on their computers. For students, the opposite is true!
This project offers the opportunity to connect different generations together and use historical documents to contribute to innovative research. This focus group is working to make the ‘Bozner Ratsprotokolle’ more accessible and providing feedback on Transkribus that will help the READ project team to refine the platform in the future. I look forward to continuing my work with the volunteers and will report back on their next milestones!’