Upcoming presentations at Rostock, Paris, Tokyo and Jerusalem

We will present different aspects of the results of Sofer Mahir at the following upcoming conferences :

1. Machine Learning and Data Mining for Digital Scholarly Editions, Rostock 9-10 June 2022

2. Documents anciens et reconnaissance automatique des écritures manuscrites, ENC, Paris 23-24 June 2022

3. DH2022 Tokyo, 25-29 July 2002

4. World Congress of Jewish Studies, Jerusalem, 8-12 August 2022

Stay tuned for further news.

International Conference on Document Analysis and Recognition 2021

We have two presentations at this years ICDAR workshops.

The first, in the Historical Document Imaging and Processing workshop (HIP) presents our first generalized segmentation and transcription models and a large open source dataset for medieval Hebrew.

The second, in the computational paleography workshop treats the automatic detection of insertion spots for interlinear and marginal additions.

Presentation of the Sofer Mahir project and eScriptorium at the DHJewish conference in Luxemburg, January 2021

by Daniel Stoekl Ben Ezra · 04/02/2021

Stökl Ben Ezra, D., Lapin, H., Lolli, E. Jablonski, P. Sofer Mahir: Opening Up Rabbinic Manuscripts Towards Scholarly Editions, DHJewish conference at the University of Luxembourg, 11-14 January, 2021. watch video.

Presentation at MITH in April 2019

Tuesday, April 2, 2019 – 12:30pm to 1:45pm
MITH, 0301 Hornbake Library
University of Maryland
Daniel Stoekl Ben Ezra

Presentation at Princeton University April 2019

Sofer Mahir, Tikkoun Sofrim, eRabbinica and eScriptorium will be presented at a lecture entitled

Artificial Intelligence, Citizen Science and Medieval Hebrew Manuscripts

at Princeton University on Friday April 5, 2019 at noon in room 203 in the Scheide Caldwell house. If you intend to come please inform Baru Saul from the Judaic Studies programme

Sofer Mahir

This blog covers the Sofer Mahir project. This project funded by a private foundation for the period from September 2018 until August 2021 deals with the application of cutting edge document analysis, handwritten text recognition and other machine learning on manuscript images of several European and American libraries and the National Library of Israel for the creation of an open source repository for precise transcriptions of tannaitic rabbinic literature.
Expected readers include scholars in Jewish studies and manuscript studies as well as digital and computational humanities.
This project is in close interaction but distinct from the Tikkoun Sofrim blog.
The Hebrew expression Sofer Mahir means “tachygraph” while Tikkoun Sofrim means “scribal correction”. The first deals mainly with automatic layout analysis and automatic transcription while the second deals mainly with the application of gamification, machine learning and crowdsourcing to correct these automatic transcriptions. They run over different periods.