Resources 2026

It is expected that the students attending the School will use their own PC for the hands-on laboratories. Under each topic there will be (when available) recommendations and suggestions about software and tools that will be used during the lessons and the laboratories.
Under each topic there will be also copy of the slides used during the lessons, as they become available, and “suggested readings” about the topics presented during the School.

Welcome to the Summer School 2026 (slides)

 

CLARIN (Common Language Resources and Technology Infrastructure) is a relevant resource for projects in the Humanities. It is a European research infrastructure designed to make digital language resources, tools, and services easily accessible. You can find all the information at the pages below.

CLARIN in a nutshell
CLARIN learning hub
CLARIN resource families
CLARIN knowledge centers
CLARIN Virtual Language Observatory
 

Refresher on computers and networking (V. Casarosa)

At this link you can find the slides for a refresher on Computer Architecture and Data Representation.
At this link you can find the slides for a refresher on Networking and Linked Data.

At this link you can find the slides for a brief introduction to CLARIN.

Selected suggested readings
– A brief history of computers
– A brief history of the Internet
– Introduction to Unicode

Selected suggested readings on LOD (Linked Open Data)
– Resource Description Framework: a RDF Primer
– A book on Linked Open Data
 

Designing a project in Digital Public History (E. Salvatori)

At this link you can find the slides used for this lecture.
At this link you can find some material to be used during the lecture.
 

Methods and tools for digital philology (R. Rosselli Del Turco)

Before the lecture please install on your PC the Visual Studio Code (here is the link), including the two extensions Scholarly XML (by R. Viglianti) and Live Server (by R. Dey). Complete instructions can be found in the folder “doc” at the link here below.

At this link you can find all the instructions and material needed for this lecture.
 

Computational Linguistics and Generative AI: An Introduction (R. Sprugnoli)

At this link you can find all the instructions and material needed for this lecture.
 

Historical GIS (T. Alvarenga de Oliveira)

At this link you can find all the instructions and material needed for this lecture.
 

AI Meets the Archive: Refining Generative Tools for Historical Research (S. Ross)


Recommended bibliography

  • A Public Record at Risk: The Dire State of News Archiving in the Digital Age
    Go to the web site
  • Tianyang Zhong, Zhenyuan Yang, Zhengliang Liu, Ruidong Zhang, Yiheng Liu, Haiyang Sun, Yi Pan et al. “Opportunities and challenges of large language models for low-resource languages in humanities research.” arXiv preprint arXiv:2412.04497 (2024)
    Click here to download the paper
  • Zhiwei Ma, Javier E. Santos, Greg Lackey, Hari Viswanathan, and Daniel O’Malley. “Information extraction from historical well records using a large language model.” Scientific Reports 14, no. 1 (2024): 31702.
    Click here to download the paper
  • Yannis Assael Thea Sommerschield, Brendan Shillingford, Mahyar Bordbar, John Pavlopoulos, Marita Chatzipanagiotou, Ion Androutsopoulos, Jonathan Prag, and Nando de Freitas. “Restoring and Attributing Ancient Texts Using Deep Neural Networks.” Nature (London) 603, no. 7900 (2022): 280–83. https://doi.org/10.1038/s41586-022-04448-z.
    Click here to download the paper
  • Yifan Zeng, 2024, HistoLens: An LLM-Powered Framework for Multi-Layered Analysis of Historical Texts
    Click here to download the paper
  • Carlos-Emiliano González-Gallardo, Hanh Thi Hong Tran, Ahmed Hamdi, Antoine Doucet, Giorgio Maria Di Nunzio, Mickaël Coustaty, Francesco Gelati, et al. “Leveraging Open Large Language Models for Historical Named Entity Recognition.” In Linking Theory and Practice of Digital Libraries, 15177:379–95. Switzerland: Springer, 2024. https://doi.org/10.1007/978-3-031-72437-4_22.
    Click here to go to the editor site. The paper is behind paying walls.

For this session please ensure that you have registered for a free license with the following LLMs (if you do not have one already).
All three tools will be used for team activities.

Link to Activity 1
Link to Activity 2
 

Reading the past with AI: eScriptorium and Transkribus (F. Boschetti)

At this link you can find the slides used for this lecture.