Many texts in the world’s documentary record remain only partially understood—encoded, fragmentary, or written in undeciphered scripts and languages. Such materials challenge conventional models of linguistic structure and interpretation.
This talk examines how AI-driven computational methods can support the systematic analysis of hidden codes and unknown languages. A concise overview of methodological developments situates current approaches within a broader historical trajectory, from early statistical and structuralist techniques to today’s hybrid machine-learning pipelines that combine neural models with rule-based and philologically informed components.
Through selected case studies, the talk highlights both the potential and the limitations of AI when working with sparse and uncertain data, underscoring the continued importance of expert linguistic judgment. I will demonstrate how computational and humanistic perspectives can be productively integrated in the effort to understand some of the world’s most enigmatic texts.
Coffee and saffron buns will be served during the event.
Beáta Megyesi is Professor of Computational Linguistics at Stockholm University. She earned her Ph.D. from the Royal Institute of Technology (KTH) and served as associate and full professor at Uppsala University. She has led numerous externally funded research initiatives and is Principal Investigator of DECRYPT (Swedish Research Council, 2018–2024) and DESCRYPT (Riksbankens Jubileumsfond, 2025–2032), projects that advance computational methods and research infrastructures for historical cryptology and the automatic analysis of rare scripts. Megyesi is the author of more than 120 scientific publications and has delivered many keynote lectures at international conferences. Her previous leadership roles include President of the Northern European Association for Language Technology, Chair of the Linguistics Review Panel at the Swedish Research Council, and Head of the Department of Linguistics and Philology at Uppsala University.
The seminar is a joint arrangement between Humlab and the Department of Language Studies.