Slavic Natural Language Processing 2025

ITSERR – Italian Strengthening of the ESFRI RI RESILIENCE – took part in the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025), held in Vienna, with a contribution on the diachronic analysis of Church Slavonic. Maria Cassese presented the paper “DIACU: A dataset for the DIAchronic analysis of Church Slavonic”, co‑authored by Maria Cassese, Giovanni Puccetti, Marianna Napolitano and Andrea Esuli, which introduces DIACU, a new large‑scale dataset that aggregates and annotates 652 texts from different historical variants of Church Slavonic and related Slavic languages to support both linguistic research and machine‑learning approaches to temporal and regional attribution. For more information, see the workshop programme.