Sampo Pyysalo profile picture
Sampo
Pyysalo
University Research Fellow, Data analytics

Areas of expertise

natural language processing
machine learning
scientific text mining

Biography

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.

Teaching

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.

Research

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.

Publications

Sort by:

The birth of Romanian BERT (2020)

Empirical Methods in Natural Language Processing, Annual Meeting of the Association for Computational Linguistics
Stefan Dumitrescu, Andrei-Marius Avram, Sampo Pyysalo
(Vertaisarvioitu artikkeli konferenssijulkaisussa (A4))

From Web Crawl to Clean Register-Annotated Corpora (2020)

Web as Corpus Workshop
Laippala Veronika, Rönnqvist Samuel, Hellström Saara, Luotolahti, Juhani, Repo Liina, Salmela Anna, Skantsi Valtteri and Pyysalo Sampo
(Vertaisarvioitu artikkeli konferenssijulkaisussa (A4))

Toward Multilingual Identification of Online Registers (2019)

Nordic Conference on Computational Linguistics, Linköping Electronic Conference Proceedings
Veronika Laippala, Roosa Kyllönen, Jesse Egbert, Douglas Biber, Sampo Pyysalo
(Vertaisarvioitu artikkeli konferenssijulkaisussa (A4))