Hanna-Mari Kupari profile picture
Hanna-Mari
Kupari
Doctoral Researcher, Digital Language Studies, Chinese, French, German, Italian, Spanish
filosofian maisteri - Master of Arts
Medieval Latin with corpus linguistics methods

Contact

Arcanuminkuja 1
20500
Turku

Areas of expertise

Medieval Latin
corpus linguistics
TEI-xml
automatic morpho-syntactic parsing

Biography

I am a doctoral researcher in digital language studies at the University of Turku, funded by the Emil Aaltonen Foundation. My research combines medieval Latin textual data with state-of-the-art machine learning methods. I hold a Master’s degree in Classical Philology with a specialization in Latin, focusing on medieval Latin. My primary interests include the study of grammar, quantitative methodologies, and local history.

In addition to my academic work, I am passionate about science communication and have published numerous popularized articles. I have also been an active member of the Tohtoriverkosto society, contributing to its activities.


Teaching

Teaching Experience

  • University of Tartu, Estonia
    • Practical Workshop: Automatic morpho-syntactic annotation of large language corpora using the Universal Dependencies framework (spring 2024). This five-session workshop for PhD students and staff covered theory, terminology, parsing tools, and practical treebank creation.
    • Lecture for the Digital Resources course in Classical Philology: Treebanks and automatic linguistic annotation for Classical Languages (spring 2024).
    • University of Turku, Finland
      • Digital Interaction Lecture Course (spring 2024): One lecture: Using computer-assisted methods for parsing grammar.
      • Corpus Linguistics and Language Technology (fall 2023 and 2024): Five and six lectures. Topics included student projects, ethics and large language models, named-entity recognition, sentiment analysis, automatic morpho-syntactic parsing, representing language as vectors, and supervised and unsupervised machine learning.
      • Linguistic Landscapes Course (spring 2023): A lecture titled Historiallisten kirjallisten lähteiden näkökulmia kielimaisemiin Turussa, co-taught with Professor Marko Lamberg (2023-03-15).

 

Research

Modern Methods for Medieval Texts

In my digital humanities doctoral dissertation, I investigate medieval apostolic penitentiary documents and the Registrum Ecclesiae Aboensis copybook using corpus linguistics methods. My research focuses on language use and linguistic variation (register analysis) in Medieval Latin, utilizing metadata-enriched and morpho-syntactically annotated corpora. Committed to promoting open-access research, I openly publish all my code, data, and results alongside my publications.

I am a member of the TurkuNLP and TUCEMEMS research groups.

Grants

My work is supported by several grants, including the Emil Aaltonen Foundation grant (2022–2024), Turku University Foundation travel grant (2023), University of Turku research grants (2022, 2021), Finnish Cultural Foundation Varsinais-Suomi Regional Fund grant (2021), and Uskelan Opintorahastosäätiö grant (2020). I have also received Turku University Foundation Villa Tammekann grants for research visits to Tartu, Estonia (2023, 2024).

In 2024, I was awarded the Otto A. Malm mobility grant and the Kordelin Foundation full-time working grant. In January and December 2024, I conducted my research at the Finnish Institute in Rome, visiting the penitentiary archive and libraries. During the fall of the same year, I visited the History Department at Harvard University to engage with their research in digital methods.




Publications

Sort by:

Avoin tiede ja tutkimusinfra (2024)

Hiiskuttua: Turun yliopiston humanistisen tiedekunnan verkkolehti
Kupari, Hanna-Mari; Leinonen, Päivi
(D1 Artikkeli ammattilehdessä)

FinGPT: Large Generative Models for a Small Language (2023)

Conference on Empirical Methods in Natural Language Processing
Luukkonen Risto, Komulainen Ville, Luoma Jouni, Eskelinen Anni, Kanerva Jenna, Kupari Hanna-Mari, Ginter Filip, Laippala Veronika, Muennighoff Niklas, Piktus Aleksandra, Wang Thomas, Tazi Nouamane, Scao Le Teven, Wolf Thomas, Suominen Osma, Sairanen Samuli, Merioksa Mikko, Heinonen Jyrki, Vahtola Aija, Antao Samuel, Pyysalo Sampo
(Vertaisarvioitu artikkeli konferenssijulkaisussa (A4))