On June 29–30, 2026, I had the pleasure of taking part in the seminar More Human Through Digital: Digital Humanities through Lexicography, Lemmatization, Artificial Intelligence, & More, organized by Sadurní Martí and Miriam Cabré at the University of Girona, a city I am always very happy to return to.
The seminar brought together scholars working on digital lexicography, textual scholarship, historical corpora, automatic transcription, mapping, and artificial intelligence. The full program is available here.
Among the many stimulating presentations, Salvatore Arcidiacono (University of Catania) introduced the work of the Opera del Vocabolario Italiano and LexiCad, a dictionary-writing system used to manage and analyze the extensive textual corpus that supports the creation of historical Italian dictionaries. He also discussed related initiatives built around the same corpus and digital infrastructure, including the Tesoro della Lingua Italiana delle Origini and the Vocabolario Dantesco.
Miriam Cabré and her PhD student Ivan Vera presented the past and future of TrobEu. Trobadours and European Identity, a project that maps the circulation and mobility of troubadours. I was especially interested in their move from ArcGIS to QGIS, since it makes the project more open and sustainable. The first results of the new QGIS map are already available here, and it was exciting to see how the project is evolving through the use of open-source tools.
Sadurní Martí presented the ongoing transformation of RIALC: Repertorio informatizzato dell’antica letteratura catalana into the forthcoming BibliotecaMedieval.cat, a new digital philological resource that will bring together the largest corpus of medieval Catalan texts, encoded in XML-TEI, lemmatized, and organized within a structured textual database. I am very much looking forward to seeing how this ambitious initiative develops!!
Another thing I found especially impressive was the sheer number of interconnected projects being developed by the Catalan research team Narpan.net, devoted to the literature and culture of the late Middle Ages. These include Cançoners DB, on medieval Catalan poetry and songbooks; Eiximenis DB; Llull DB; Translat DB, dedicated to translations into medieval Catalan up to 1500; and Sciencia.cat, which explores the place of science in Catalan culture during the Middle Ages and the Renaissance. All together, these projects form a incredibly rich and ambitious digital ecosystem.
Other presentations introduced equally valuable initiatives. Roberta Romeo discussed the Vocabolario del Siciliano Medievale, while Antonella Zammataro presented ArchivIA, an integrated system for the digital processing of texts. Enric Saguer presented Arxiversa, a project that explores the automatic transcription of the historical Ofici d’Hipoteques de Girona (1768-1805) records and their potential for reconstructing social history “from below.”
My own presentation had the rather ambitious title Digital Scholarly Editing in the Age of AI. In it, I reflected on how digital technologies are reshaping philology and on the need to move toward a more data-driven approach, or perhaps even an “AI philology.” I also explored some of the possibilities that generative AI tools are beginning to offer for textual scholarship and digital editing.
The seminar offered an excellent opportunity to learn about ongoing digital projects developed across different linguistic and scholarly traditions, while also reflecting on the possibilities of collaboration on many differents fronts such as digital lexicography, textual editing, data modeling, sustainability, and access. Hopefully, there will be a second round of “More Human Through Digital”.