Liina Repo
Filosofian maisteri – Master of Arts
liina.t.repo@utu.fi Arcanuminkuja 1 Turku |
corpus linguistics; computational linguistics; Late Modern English; register studies
Digital Language Studies
I am a doctoral researcher in Digital Language Studies. My interests revolve around using computational methods with historical language.
In my research, I am interested in using automatic text classification methods to model noisy historical data. More specifically, I focus on predicting and modelling registers (text varieties) from large Late Modern English datasets with machine learning methods.
Other research projects I've participated in:
- Project researcher, Prosovar project (Digilang)
- Project researcher, Universal Parsebanks project (Digilang)
- Project assistant, Structuring Language Use Across Multilingual Web Corpora
- Filosofian tohtoreiden urapolkupuheenvuorot: moniosaaminen voimavarana (2024)
- Hiiskuttua: Turun yliopiston humanistisen tiedekunnan verkkolehti
- From Discrete to Continuous Classes: A Situational Analysis of Multilingual Web Registers with LLM Annotations (2024) Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities Henriksson, Erik; Myntti, Amanda; Hellström, Saara; Erten-Johansson, Selcen; Eskelinen, Anni; Repo, Liina; Laippala, Veronika
- Intersecting Register and Genre: Understanding the Contents of Web-Crawled Corpora (2024) Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities Myntti, Amanda; Repo, Liina; Freyermuth, Elian; Kanner, Antti; Laippala, Veronika; Henriksson, Erik
- Towards Automatic Register Classification in Unrestricted Databases of Historical English (2024) Linguistics across Disciplinary Borders : the March of Data Repo Liina, Hashimoto Brett, Liimatta Aatu, Saario Lassi, Säily Tanja, Tiihonen Iiro, Tolonen Mikko, Laippala Veronika
- In search of founding era registers: automatic modeling of registers from the corpus of Founding Era American English (2023)
- Digital Scholarship in the Humanities
- Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model (2022) Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change Rastas Iiro, Ryan Yann, Tiihonen Iiro, Qaraei Mohammedreza, Repo Liina, Babbar Rohit, Mäkelä Eetu, Tolonen Mikko, Ginter Filip
- Beyond the English web: Zero-shot cross-lingual and lightweight monolingual classification of registers (2021) Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop Repo Liina, Skantsi Valtteri, Rönnqvist Samuel, Hellström Saara, Oinonen Miika, Salmela Anna, Biber Douglas, Egbert Jesse, Pyysalo Sampo, Laippala Veronika
- From Web Crawl to Clean Register-Annotated Corpora (2020) Proceedings of the 12th Web as Corpus Workshop Laippala Veronika, Rönnqvist Samuel, Hellström Saara, Luotolahti, Juhani, Repo Liina, Salmela Anna, Skantsi Valtteri and Pyysalo Sampo
UTU Research Portal