
Mining the Vatican Secret Archives with TensorFlow w/ Elena Nieddu - TWiML Talk #243
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Transcribing Vatican Manuscripts
This chapter explores the challenges of transcribing medieval manuscripts from the Vatican Registers, highlighting the limitations of traditional OCR and the shift toward machine learning solutions. It discusses the complexities of annotation required for accurate transcription and the innovative strategies employed to improve efficiency, such as annotating individual characters. The narrative emphasizes the importance of expert knowledge and a novel cloud platform for enhancing symbol recognition in historical texts.
Transcript
Play full episode