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

Latin
Middle Ages
corpus linguistics
TEI-xml
automatic morpho-syntactic parsing

Teaching

KKLT0040-3004 Corpus Linguistics and Language Technology for undergraduates, fall 2023. Five lectures. Topics covered: student project, ethics and large language models, named-entity recognition, sentiment analysis, automatic morpho-syntactic parsing, reprsenting language as vectors and supervised and unsupervised machine learning. Käsiteltävät aihepiirit: opiskelijaprojekti, eettiset näkökulmat ja generatiiviset kielimallit, nimitettyjen entiteettien tunnistus, sentimenttianalyysi, automaattinen morfosyntaktinen jäsennys, kielen esittäminen vektoreina sekä ohjattu ja ohjaamaton koneoppiminen.

Linguistic landscapes course for undergraduates, 2023 spring, teacher Hanna Lantto. One lecture 2023-03-15 with professor Marko Lamberg "Historiallisten kirjallisten lähteiden näkökulmia kielimaisemiin Turussa"


Research

In my doctoral dissertation I am researching the apostolic penitentiary documents from 1410 to 1526 AD with digital linguistics methods. I'm also exploring the linguistic variation (i.e. register analysis) of Medieval Latin. Production of an open-access database of linguistically analysed penitentiary documents.

Member of TurkuNLP and TUCEMEMS research groups.


My work is made possible by the Emil Aaltonen säätiö -fund 2022 and 2023, Turku University Foundation travel grant 2023, University of Turku research grants 2022 and 2021, The Finnish Cultural Foundation Varsinais-Suomi Regional Fund grant 2021, Uskelan opintorahastosäätiö 2020

Publications

Sort by:

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))