About

This is a ‘work in progress’ blog associated with eScripta, the Digital Humanities team within the Scripta project at Université Paris Sciences et Lettres. It will feature regular discussions from members of the project team and selected external contributions. Articles will comprise a mixture of presentations of work in progress, discussions of methodological challenges, and notices of future events and related news. The target audience is those in Computational and Digital Humanities and (Historical) Document Analysis, including related specialisations such as Computational and Digital Palaeography (modelling and describing script, OCR and HTR, layout analysis, and more).

current schema

Members of the eScripta team are associated with and drawing on the following projects:

  • Scripta PSL: the overarching project of which eScripta is a part.
  • Kraken: the free, open-source, open-model software for Handwritten Text Recognition (HTR), developed by Ben Kiessling of the eScripta group and being used in the eScripta system.
  • Archetype: the free, open-source software developed by Peter Stokes of eScripta and a team based at King’s Digital Lab (King’s College London), for deep, structured annotation of palaeography, texts, and other written communication. 
  • TEI-Publisher: a platform by eXist for publishing TEI for critical editions as in the eRabbinica Mishnah edition
  • Pyrrha: a tool for postcorrection of POS tagging and lemmatization developed at the ENC.

About Scripta-PSL

The programme “Scripta-PSL, The History and Practices of Writing” aims at integrating the fundamental sciences that deal with written artefacts (palaeography, codicology, epigraphy, history of the book, etc.), with other disciplines in the humanities and social sciences (linguistics, history, anthropology, etc.), together with digital and computational humanities, around the study of writing. The program, a Strategic Interdisciplinary Research Initiative (IRIS) of PSL, is supported by EPHE and EFEO, in association with ENS, ENC, EHESS, Collège de France and IRHT (CNRS).

The research programme consists of six areas: “Writing and languages”; “Pages–Visual Fields for Reading”; “Exposed Writings–Inscriptions in Space”; “Documentary Practices, Old and New”; “The Transmission of the Written Word–Building Canons”; “Challenges in Digital Scholarly Editing”. The digital and computational team will focus on tools for computer vision and (semi-)automatic classification, especially adapted to writing from pre-typographic and/or non-Latin cultures.

For further information, see https://scripta.psl.eu/