Staff profile

I am a historian of the Greek world and an epigrapher, Anglo-Italian by birth and Scandinavian by surname. I gained my BA in Classics at the University of Pavia (Ghislieri College), alongside a parallel degree from the Institute of Advanced Study (IUSS) of Pavia. I then moved to Oxford for an MSt in Greek History and a DPhil in Ancient History.

During my postdoctoral meanderings, I was an Award holder at the British School at Rome (2020), Fellow in Hellenic Studies at Harvard’s CHS (2021–22), Marie Skłodowska-Curie Fellow at Ca’ Foscari University of Venice (2021–23), and Leverhulme Fellow at the University of Nottingham (2024–25). I joined the Department of Classics and Ancient History at Durham as Assistant Professor in September 2025.

My research develops and applies Machine Learning models to ancient Mediterranean written cultures, exploring new ways to understand and write about history, and challenging how we think about the ancient world using AI (while also using ancient data to reflect on how we think about AI itself). I also work on the epigraphy and archaeology of Greek Sicily.

 

Research projects

Ithaca

Ithaca is the first deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. The model is designed to assist and expand the historian’s workflow: its architecture focuses on collaboration, decision support and interpretability. Research now continues on investigating the new contextualisation function of the upgraded model. 

I co-led this project with Google DeepMind and funded by the MSCA - EU commission.

• Read the article and the release blogpost.

• Use the free online interface for your research here: https://predictingthepast.com/

Consuming the East in Sicily

The eastern Greek transport amphorae from the necropoleis of Himera reveal new insights into the colony's extra-regional trade (mid-7th to 5th century BCE). I am responsible for the study of the inscriptions on the transport amphorae from the necropoleis. I also enjoy publishing new epigraphic material from Himera and its hinterland.

I am a cooperation partner of this project, which is led by the University of Vienna - FWF Austrian Sciences Fund.

• Visit the project website.

Aeneas

Aeneas is the first generative neural network for contextualizing Roman inscriptions. Aeneas retrieves textual and contextual epigraphic parallels, leverages visual inputs, handles arbitrary-length text restoration, and advances the state of the art in key tasks (restoring, dating and placing inscriptions). Research now continues on performance analysis and the contextualisation function. 

I co-led this project with Google DeepMind and funded by the Leverhulme Trust.

• Read the article and the release blogpost.  

• Use the free online interface for your research here: https://predictingthepast.com/.

Office hours

My office is 111, 37 North Bailey, Durham DH1 3ET; my office hours are Tuesdays 10:00-11:00am.

Please select a time slot at this link.

Supervision and mentorship

PhD Supervision: I would be interested in supervising PhD students working on Greek history (particularly Greek religion, epigraphy, colonisation and settlement, and ancient Sicily) and on AI-digital approaches to ancient languages. Please make an appointment with me via email to discuss your interests.

Postdoctoral mentorship: If you’re interested in applying for a Leverhulme EC, British Academy or Marie Sklodowska-Curie fellowship (or other schemes), or intend to carry out a research secondment at Durham with a project on Greek history or on AI for the ancient world, drop me an email and I’d be very happy to talk more.

School talks and outreach

I am always glad to give school talks on Digital Humanities and AI for the Ancient World. 

• Ancient Greek History
• Epigraphy
• Machine Learning for ancient languages
• Ancient Sicily (c. 700 BCE - 300 BCE)
• Greek religion
• Digital Humanities

• 2027: Chair, ‘Epigraphy and Artificial Intelligence’ parallel session, CIEGL 2027, Bologna:
• 2026: Member of the Sectoral Scientific Council (SSC) for Creativity, Art and Humanities - Hellenic Republic, Ministry of Development:
• 2025: Google Developer Expert:
• 2024 - 2025: Leverhulme EC Fellow, University of Nottingham - Leverhulme Trust:
• 2024: Chair, 'Machine Learning for Ancient Languages' workshop, ACL Bangkok:
• 2022 - 2024: Google Cloud Research Innovator:
• 2022: Ghislieri Prize (Collegio Ghislieri):
• 2021 - 2023: Marie Skłodowska-Curie Fellow, Ca' Foscari University of Venice - European Commission:
• 2021 - 2022: CHS Fellow in Hellenic Studies, Harvard University:
• 2021: Giuseppe Nenci Prize (Scuola Normale di Pisa):
• 2020 - 2020: Ralegh Radford Rome Award, British School at Rome:
• 2017 - 2019: Craven University Fellow, Faculty of Classics - University of Oxford:

Chapter in book

• Iscrizioni su anfore greco-occidentali a Himera
  
  Sommerschield, T. (2025). Iscrizioni su anfore greco-occidentali a Himera. In B. Bechtold & S. Vassallo (Eds.), Produzioni e circolazione delle anfore greco-occidentali (VI-V sec. a.C.): il contributo dalle necropoli di Himera (pp. 135-146). BABESCH.
• Sicilia epigrafica: dai depositi alla valorizzazione
  
  Prag, J., & Sommerschield, T. (2021). Sicilia epigrafica: dai depositi alla valorizzazione. In R. Panvini, F. Nicoletti, N. Condorelli Caff, & M. Bevacqua (Eds.), Beni Culturali: dai depositi alla valorizzazione. Modi, forme, esperienze, norme (pp. 117-136). Mesogheia - Edizioni Lussografica.
• A New Sicilian Curse Corpus: A Blueprint for a Geographical and Chronological Analysis of Defixiones from Sicily
  
  Sommerschield, T. (2019). A New Sicilian Curse Corpus: A Blueprint for a Geographical and Chronological Analysis of Defixiones from Sicily. In R. Morais, D. Leão, D. Rodríguez Pérez, & D. Ferreira (Eds.), Greek Art in Motion (pp. 489-501). Archaeopress.

Conference Paper

• Restoring ancient text using deep learning: A case study on Greek epigraphy
  
  Assael, Y., Sommerschield, T., & Prag, J. (2019). Restoring ancient text using deep learning: A case study on Greek epigraphy. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 6368-6375). https://doi.org/10.18653/v1/D19-1668

Journal Article

• Contextualizing ancient texts with generative neural networks
  
  Assael, Y., Sommerschield, T., Cooley, A., Shillingford, B., Pavlopoulos, J., Suresh, P., Herms, B., Grayston, J., Maynard, B., Dietrich, N., Wulgaert, R., Prag, J., Mullen, A., & Mohamed, S. (2025). Contextualizing ancient texts with generative neural networks. Nature, 645, 141-147. https://doi.org/10.1038/s41586-025-09292-5
• Machine Learning for Ancient Languages: A Survey
  
  Sommerschield, T., Assael, Y., Pavlopoulos, J., Stefanak, V., Senior, A., Dyer, C., Bodel, J., Prag, J., Androutsopoulos, I., & de Freitas, N. (2023). Machine Learning for Ancient Languages: A Survey. Computational Linguistics, 49(3), 703-747. https://doi.org/10.1162/coli_a_00481
• Le storie di Eracle narrate a Terravecchia di Cuti: un nuovo louterion iscritto
  
  Sommerschield, T., & Vassallo, S. (2023). Le storie di Eracle narrate a Terravecchia di Cuti: un nuovo louterion iscritto. Sicilia Archeologica, 114, 33-47. https://doi.org/10.48255/2283-3307.SICA.114.2023.02
• Restoring and attributing ancient texts using deep neural networks
  
  Assael, Y., Sommerschield, T., Shillingford, B., Bordbar, M., Pavlopoulos, J., Chatzipanagiotou, M., Androutsopoulos, I., Prag, J., & de Freitas, N. (2022). Restoring and attributing ancient texts using deep neural networks. Nature, 603(7900), 280-283. https://doi.org/10.1038/s41586-022-04448-z