ARCHiVe Online Academy | Workshop on dhSegment data extraction from texts - Fondazione Giorgio Cini Onlus

ARCHiVe Online Academy | Workshop on dhSegment data extraction from texts

plus Nov, 27Dec, 11 2020

dhSegment workshop 

27 November, 4 and 11 December 2020

Three lessons, two hours each, from 5pm to 7pm


The third workshop presents the potential and use of dhSegment, a tool developed by the Digital Humanities Laboratory (DHLAB) of the École Polytechnique Fédérale de Lausanne. dhSegment is an innovative system that uses machine learning algorithms to process different types of archive documents and automatically extract information from them.

The course will take place as a real workshop, during which teachers will assist users step by step in using the software. For this reason the places to participate live on Zoom will be limited to 30.

Teaching will be in English. When watching the workshop on YouTube, users can turn on subtitles in English or other languages.


Detailed programme

27 November (5-7pm)
Presentation of the DHSegment tool from a theoretical and practical point of view. Practical workshop of annotation on historical documents
4 December (5-7pm)
Practical workshop of DHSegment to extract elements from historical documents that have been previously annotated.
11 December (5p-7m)
Presentation and discussion on the results of the extraction.
Frédéric Kaplan, Remy Petitpierre, Isabella di Lenardo (EPFL)


How to paticipate

The workshop with limited places will be held live on the Zoom platform; registration is required by completing the following online application form by 12 noon on 23 November 2020.


Once your application arrives, you will receive an immediate reply and confirmation of participation.

If there are no places left for the live session, you will be sent a link so that you can watch the workshop later on our YouTube channel.