Sampo Pyysalo
sampo.pyysalo@utu.fi |
natural language processing; machine learning; scientific text mining
I am a researcher in the TurkuNLP group (https://turkunlp.org/) and Research Fellow at the Department of Computing, University of Turku. My work focuses on machine learning for natural language processing, with particular application domains including scientific text mining, Finnish language technology, and large language models.
After defending my PhD thesis in computer science at the University of Turku, I held researcher positions at the University of Tokyo, University of Manchester and University of Cambridge before returning to the University of Turku in 2019.
The primary focus of my research is on natural language processing using machine learning approaches, with recent emphasis on deep learning methods and large language models. I have been working on scientific text mining as an application area for nearly 20 years, with specific focus on the English biomedical literature, and have in recent years also addressed a variety of tasks in the processing of Finnish text as well as multi- and cross-lingual applications. My work covers the full range of natural language processing development from initial task design to the development of practical applications and organizing community challenges, including also running manual annotation efforts and developing annotation tools and machine learning methods for various natural language processing tasks.
My current teaching focuses on the natural language processing study module shared between the departments of Languages and Computing, with courses ranging from introductory to a course on deep learning for natural language processing.
- An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT) (2025)
- Annual Meeting of the Association for Computational Linguistics
- Annotated textual dataset PV600 of perovskite bandgaps for information extraction from literature (2025)
- Scientific Data
- Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code (2025) Proceedings of the 31st International Conference on Computational Linguistics : Industry Track Nakamura, Taishi; Mishra, Mayank; Tedeschi, Simone; Chai, Yekun; Stillerman, Jason T.; Friedrich, Felix; Yadav, Prateek; Laud, Tanmay; Chien, Vu Minh; Zhuo, Terry Yue; Misra, Diganta; Bogin, Ben; Vu, Xuan-Son; Karpinska, Marzena; Dantuluri, Arnav Varma; Kusa, Wojciech; Furlanello, Tommaso; Yokota, Rio; Muennighoff, Niklas; Pai, Suhas; Adewumi, Tosin; Laippala, Veronika; Yao, Xiaozhe; Junior, Adalberto Barbosa; Drozd, Aleksandr; Clive, Jordan; Gupta, Kshitij; Chen, Liangyu; Sun, Qi; Tsui, Ken; Moustafa-Fahmy, Nour; Monti, Nicolo; Dang, Tai; Luo, Ziyang; Bui, Tien-Tung; Navigli, Roberto; Mehta, Virendra; Blumberg, Matthew; May, Victor; Nguyen, Hiep; Pyysalo, Sampo
- Got Compute, but No Data: Lessons From Post-training a Finnish LLM (2025)
- NEALT proceedings series
- LSD600: the first corpus of biomedical abstracts annotated with lifestyle–disease relations (2025)
- Database: The Journal of Biological Databases and Curation
- Poro 34B and the Blessing of Multilinguality (2025)
- NEALT proceedings series
- Question Answering models for information extraction from perovskite materials science literature (2025)
- Communications materials
- Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation (2025) Proceedings of the Second Conference on Language Modeling, COLM 2025 Myntti, Amanda; Henriksson, Erik; Laippala,Veronika; Pyysalo, Sampo
- Scaling Data-Constrained Language Models (2025)
- Journal of Machine Learning Research
- The STRING database in 2025: protein networks with directionality of regulation (2025)
- Nucleic Acids Research
- A New Massive Multilingual Dataset for High-Performance Language Technologies (2024)
- LREC Proceedings
- Application of the Question Answering method to extract information from materials science literature (2024) Sipilä, Matilda; Mehryary, Farrokh; Pyysalo, Sampo; Ginter, Filip; Todorović Milica
- Building Question-Answer Data Using Web Register Identification (2024)
- LREC Proceedings
- CoNECo: a Corpus for Named Entity recognition and normalization of protein Complexes (2024)
- Bioinformatics Advances
- Improving dictionary-based named entity recognition with deep learning (2024)
- Bioinformatics
- Lifestyle factors in the biomedical literature: An ontology and comprehensive resources for named entity recognition (2024)
- Bioinformatics
- Linguistic variation beyond the Indo-European web: Analyzing Turkish web registers in TurCORE (2024)
- Register studies
- Question Answering models for information extraction from perovskite materials science literature (2024) 2024 MRS Fall Meeting and Exhibit Sipilä, Matilda; Mehryary, Farrokh; Pyysalo, Sampo; Ginter, Filip, Todorović, Milica
- RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature (2024)
- Database: The Journal of Biological Databases and Curation
- STRING-ing together protein complexes: Corpus and methods for extracting physical protein interactions from the biomedical literature (2024)
- Bioinformatics



