Filip Ginter
figint@utu.fi Office: 4th floor, 451A ORCID identifier: https://orcid.org/0000-0002-5484-6103 |
natural language processing; human language technology; machine learning; deep learning; resource development
human language technology, natural language processing, machine learning applied to human language, both methodological and resource creation research
I am a researcher at the Department of Computing, University of Turku. My research is in the area of natural language processing. I belong to the TurkuNLP (turkunlp.org) research group.
I was born in 1978 in Ostrava, Czech Republic (Czechoslovakia back then). In 2001, I got a M.Sc. (tech) in computer science at the computer science department of VSB - Technical University Ostrava. My major subject was artificial intelligence. I gained a PhD in computer science in 2007. The title of my thesis is Towards Information Extraction in the Biomedical Domain: Methods and Resources.
As of 2022, I am a professor of language technology and as of 2021 the deputy director of the Department of Computing.
My primary field of research is language technology / natural language processing. In my post-PhD career, I have focused on the development of NLP tools and resources primarily for Finnish, but later also numerous other languages via the Universal Dependencies project. My work is heavy on resource development, both in terms of data and machine learning pipelines. Open science and resources play an important role in my research, much of which is carried out in the open on GitHub and as a rule, all resources are openly available for unrestricted use. I work collaboratively, especially with my younger colleagues, rather than striving for deeper, primary author inquiries.
I have been actively teaching since early on during my PhD studies. I independently prepared my first advanced level NLP course in 2004, and since ca. 2008 I have been teaching at least one course every year, substantially more during my bioinformatics lecturer appointment. While a lecturer in the bioinformatics MSc degree programme, I was lecturing international students in two cities. In 2016, I was tasked with developing and coordinating the introduction of a new 20 ECTS study module on natural language processing. This module is, with modifications, still in use and shared between the departments of Languages and Computing, both in terms of teaching and in terms of students. In 2019-2020 and 2020-2021 I was also co-lecturing, upon invitation, two courses in natural language processing in the Arcada University of Applied Sciences in Helsinki.
- Do all politicians sound the same? Comparing model explanations to human responses (2026)
- DHQ: Digital Humanities Quarterly
(A1 Refereed original research article in a scientific journal) - Large Language Models for Risk Detection in E-commerce: Reliability, Semantic Alignment, and Managerial Insights (2026)
- SN Computer Science
(A1 Refereed original research article in a scientific journal) - Measuring Social Integration Through Participation: Categorizing Organizations and Leisure Activities in the Displaced Karelians Interview Archive using LLMs (2026) Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026 Laato, Joonatan; Schroderus, Veera; Kanerva, Jenna; Kauppi, Jenni; Lummaa, Virpi; Ginter, Filip
(A4 Refereed article in a conference publication ) - Translation mining: An AI-driven taxonomy of eighteenth-century Anglo-French translation practices (2026)
- Historical Methods: A Journal of Quantitative and Interdisciplinary History
(A1 Refereed original research article in a scientific journal) - A Deep Dive into Multi-Head Attention and Multi-Aspect Embedding (2025)
- Recent Advances in Natural Language Processing
(A4 Refereed article in a conference publication ) - Annotated textual dataset PV600 of perovskite bandgaps for information extraction from literature (2025)
- Scientific Data
(A1 Refereed data article in a scientific journal) - A RAG-based LLM Approach for Data Validation and Harmonization in Ship Design (2025) 23rd Conference on Computer and IT Applications in the Maritime Industries: COMPIT’25 Bronson, Janica; Teimouri, Maryam; Gaspar, Henrique; Fonseca, Icaro; Bierkowska, Karolina; Ginter, Filip; Koelman, Herbert
(D3 Article in a professional conference publication) - Benchmarking Large Language Models for Reputational Risk Assessment in Supply Chains: A Case Study (2025) Proceedings of the 29th International Symposium on Logistics (2025) : Embedding Circularity in Supply Chains Davoodi, Laleh; Salimi, Sima; Jyote, Abul Khair; Mezei, Jozsef; Ginter, Filip
(A4 Refereed article in a conference publication ) - Creating a Historical Migration Dataset from Finnish Church Records, 1800–1920 (2025)
- Journal of Open Humanities Data
(A1 Refereed original research article in a scientific journal) - FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering (2025)
- NEALT proceedings series
(A4 Refereed article in a conference publication )



