📢 Registration is open for “The Avatars of Colonial Discourse: Computational Approaches to Colonial Media History.” Explore how computational methods can support research on colonial media archives, digitisation, silences and power. 📍 16 Oct | Belval + online 🔗Register: forms.gle/3q8XWzYtkoW5...

📰 Can LLMs help correct historical OCR? Tomorrow, Impresso joins CENL’s “AI in Libraries” webinar with Mistral AI, BnF & the British Library to discuss OCR post-correction for historical collections. 📅 Friday 10 July 2026 – 10:00 am (Paris time) 🔗 Registration: www.cenl.org/network-grou...

📻📰 The second Impresso II conference is a wrap! Last week in Lausanne, we explored links between press & radio with historians and digital humanists. 📚 The book of abstracts is available online on Zenodo:: doi.org/10.5281/zeno... 📢 Final conference CfP: impresso-project.ch/news/2026/06...

📣 Call for participation: Impresso@BnF Datathon 📍 BnF, Paris | 📅 28–30 Oct. 2026 Join a 3-day hands-on event to explore historical media across languages and modalities with the Impresso Web App, Datalab, NLP models and embeddings. 👉 Read more and register here: impresso-project.ch/news/2026/06...

📰 Recap: Impresso’s workshop at “AI through History, History through AI” explored how AI retrieval shapes historical corpus building. Through case studies on mega events and medicinal catalogues, participants tested embeddings for multilingual search, source comparison and collection building.

🏆 Our paper “Data Augmentation for Historical NER” won Best Paper at #SwissText2026, organised by UZH’s Department of Computational Linguistics and held at the University of Zurich. We compare lexical and LLM-based augmentation for historical newspapers. 📄 aclanthology.org/2026.swisste...

Data Augmentation for Historical NER: A Systematic Comparison of Lexical and LLM-based Approaches

Léa Blinière, Maud Ehrmann, Emanuela Boros, Simon Clematide, Frederic Kaplan. Proceedings of the 11th Edition of the Swiss Text Analytics Conference. 2026.

aclanthology.org

📢 Tomorrow at “AI through History, History through AI,” the Impresso team will lead a workshop on how AI-assisted retrieval shapes historical corpora, using the Impresso Datalab for multilingual and multimodal exploration. Check the conference programme: www.uni.lu/c2dh-en/even...

AI through History, History through AI

Eighth Conference on Digital Humanities and Digital History hosted at the University of Luxembourg.

uni.lu

📣 Applications are open for 3 fully funded Visiting Fellowships at C2DH, University of Luxembourg, as part of the Impresso project. 📍 Luxembourg ⏳ 3 months 💶 Travel, housing & daily allowance covered 📅 Deadline: 1 July 2026 Read more and apply here: impresso-project.ch/news/2026/06...

Last week at #DHBenelux2026, the Impresso team ran a workshop on embedding newspapers with the Impresso Datalab. 📰 Participants tested keyword, facet and embedding-based search, including text-to-text, text-to-image and image-to-image retrieval. Thanks for the great discussion! 🙏

📢 Impresso at #DHBenelux2026 Tomorrow, 2 June, the Impresso team will run a hands-on workshop in Maastricht on embedding newspapers with the Impresso Datalab. We’ll explore AI-assisted methods, embeddings, metadata, image captions and semantic enrichments for historical media analysis.

📢 Join #Impresso as a Postdoctoral Researcher in Digital/Computational History at @C2DH, University of Luxembourg. Work on “media influences” using multilingual newspaper and radio archives. 💼 6 months | Full time 🗓️ Apply by 1 July 2026 - Start dart 1 September 2026 🔗 www.uni.lu/en/jobs/post...

Postdoctoral Researcher in Digital/Computational History

uni.lu

How can historical newspapers and radio broadcasts 📰📻 be represented for ML, search, and archival fidelity? At PressMint / #LREC2026, Impresso presented a framework covering 567 titles, 73M+ items, and 24B+ tokens 📊 🔗 Read the full paper here: infoscience.epfl.ch/handle/20.50...

HIPE-2026 CLEF results are out! 🗞️📍 This edition focused on person–place relation extraction in historical newspapers, with 17 teams and 45 runs. 🥇 Congratulations to the top teams! 🎉 Results, data & scripts: hipe-eval.github.io/HIPE-2026/

🔥 Announcing HIPE-2026 at CLEF 2026! A shared task on extracting person–place relations and their temporal scope from multilingual historical texts. Open to LLM and classic IE approaches. Two tracks: accuracy 🎯 and efficiency 🚀. Details 👉 hipe-eval.github.io/HIPE-2026/

HIPE 2026 – Evaluating Accurate and Efficient Person–Place Relation Extraction from Multilingual Historical Texts

hipe-eval.github.io

📢 Impresso is hiring a Machine Learning / NLP Research Engineer at EPFL (Lausanne). Work on large-scale multilingual historical newspaper and radio archives and help build advanced NLP pipelines. 🗓️ Apply by 8 Dec 2025 📍 EPFL, Lausanne 💼 13-month contract Details: careers.epfl.ch/job/Lausanne...

📚 Impresso took part in the Assises thématiques sur l’IA by the #MinistèreCultureLU at 1535° in Differdange. We ran a workshop on the Impresso Web App and Datalab, with hands-on testing of semantic enrichments, multilingual search, notebooks, Impresso Barista 🤖☕ and embeddings. 🔗 impresso-project.ch

🔍 Impresso Seminar 2025 is coming up: a series of short online lunchtime sessions on current research in computational media history. Join us to explore new methods and findings in press history. 📅 Check the full program and register via the form on our website: impresso-project.ch/events/histo...

🔮 The Impresso team is at #HistoFest today! Explore how witchcraft, horoscopes and superstition circulated in historical newspapers. Stop by our interactive stand to try the fortune-telling app and print your own historical horoscope 🕯️📜 📅 15 Oct 2025 – 16:30 📍 Belval Plaza (Esch-sur-Alzette)

🚀 Big release from Impresso! Introducing the Datalab: programmatic access via API + Python, with notebooks for geospatial and network analysis & data enrichment. Plus: 53 new titles (BnF, Swiss partners), 180k+ issues & 11M items + new data access system. More 👉 impresso-project.ch/news/2025/09...

📣 CfP: Radio and Newspapers: What Intersections for Media History? The Impresso project is pleased to invite you to participate in its next conference, to be held in Lausanne in June 2026! 📆 The call is open until November 10, 2025 👉 Find out more here: impresso.github.io/radio-and-ne...

🇵🇹 We're happy to be part of #DH2025 in Lisbon with the Impresso Datalab Hackathon ! 📆 14 July 2025, 09:00–12:30 📍 NOVA-FCSH in Lisbon, Room B203 (TB) Scalable access + notebook-based workflows + enrichment for historical newspapers 📰📻. Check the #DH2025 program👉 dh2025.adho.org/browse-the-p...

📣 “Transmedia Histories”: We are launching a CFP for a special issue of TMG - Journal for Media History. Send us your abstracts by 🗓️ May 31! tmgonline.nl/announcement...

📢 We’re hiring a Postdoc in Digital History! Join our Luxembourg-based team for a 21-month Postdoctoral Researcher position. If interested, or know someone who might be, you can learn more and find the link to apply here 👉 impresso-project.ch/news/2025/03...

📣 Impresso is now live on Bluesky ! An interdisciplinary project exploring historical newspapers and radio archives through machine learning—across time, languages & borders. Follow us here for research updates, tools & collaborations. 🔗 Visit our homepage & explore the app: impresso-project.ch