In Codice Ratio: towards Knowledge Discovery from Medieval Manuscripts



In Codice Ratio aims at developing methods and tools to support content analysis and knowledge discovery from large collections of historical documents. The project concentrates on the collections of the Vatican Apostolic Archives (formely Vatica Secret Archives), one of the largest and most important historical archive in the world. We have developed a full-fledged system to automatically transcribe the contents of the manuscripts from Popes Registers. Our solutions relies on convolutional neural networks, crowdsourcing and statistical language models. In the first part of the workshop, we illustrate and compare the different solutions that we have explored. Then, in the second part of the workshop, we will support students in developing a simple prototype for hand written text recognition.