Histoire numérique et l’historiographie

Recording of the conference with Alban Leveau-Vallier on Creativy and AI (12 June 2024).

This chapter focuses on the dynamic nature of detail as an esthetic category and the hypothesis that interpretation in the digital medium encompasses a certain degree of modeling, understood in its double sense of building representations of objects and shaping figures in a plastic material.

Call for papers for the international conference organised by the Impresso project and the History Department of the University of Lausanne, to be held on 27 and 28 January 2025, on the theme ‘Transmedia History: Circulations, Reconfigurations and New Methodologies’.

What exactly does the Impresso project want to achieve with its research objectives in Natural language processing, design and history? What are the technical, conceptual and methodological challenges we face? How can we facilitate secure access to data with respect to copyright restrictions? These questions stood at the core of the first on-site Impresso workshop with partners which took place on 25 and 26 April 2024 at EPFL Lausanne.

The paper focuses on building and sharing documentation about the use of generative AI in DH workflows.

The aim of the study is to address the question of using generative AI in creative writing assignments starting from the hypothesis that preliminary simulations of AI-based pedagogic scenarios can help instructors to better understand the inner mechanisms of these technologies and their possible impact on the learning, assignment completion and evaluation processes. The paper presents a set of experiments with simulated student-agent interactions generated by AI chatbots and proposes a formal framework for assessing this form of “imitation game” and its possible applications in real teaching-learning environments.

Ein zweitägiger Workshop zur Nachnutzung digitalisierter historischer Zeitungen und Zeitschriften fand am 13. und 14. Mai 2024 in Darmstadt statt.

Research seminar with Prof. Sean Takats.

This article addresses the question of evaluating generative AI prompts designed for specific tasks such as linguistic linked open data modelling and refining of word embedding results.

This article proposes a linguistic linked open data model for diachronic analysis (LLODIA) that combines data derived from diachronic analysis of multilingual corpora with dictionary-based evidence.

This article proposes a small-scale investigation on the use of generative AI agents for post-OCR correction in historical datasets.

How can “transmedia” history be put into practice from both theoretical and empirical perspectives? The international conference “Transmedia History”—organised by the Impresso project and the University of Lausanne’s History Department—will gather scholars from various backgrounds around this question to exchange views on new prospects opened by digitisation and digital tools to carry out transmedia research.

LLODIA is a linguistic linked open data model for diachronic analysis.

Lecture by Dr. Inna Kizhner, C²DH visiting fellow in March-April 2024.