Filip Ginter
figint@utu.fi : 4th floor, 451A |
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.
- Paimen, piika ja emäntä. Arvot ja ammatit suomalaisessa näytelmäelokuvassa 1907–2017 (2022)
- Lähikuva
- Textual Paraphrase Dataset for Deep Language Modelling (2022) European Language Grid: A Language Technology Platform for Multilingual Europe Kanerva Jenna, Ginter Filip, Chang Li-Hsin, Skantsi Valtteri, Kilpeläinen Jemina, Kupari Hanna-Mari, Piirto Aurora, Saarni Jenna, Sevón Maija, Tarkka Otto
- Towards Automatic Short Answer Assessment for Finnish as a Paraphrase Retrieval Task (2022) Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022) Chang Li-Hsin, Kanerva Jenna, Ginter Filip
- Deep learning for sentence clustering in essay grading support (2021) Proceedings of the 14th International Conference on Educational Data Mining (EDM 2021) Chang Li-Hsin, Rastas Iiro, Pyysalo Sampo, Ginter Filip
- Fine-grained Named Entity Annotation for Finnish (2021)
- Linköping Electronic Conference Proceedings
- Finnish Paraphrase Corpus (2021)
- Linköping Electronic Conference Proceedings
- Quantitative Evaluation of Alternative Translations in a Corpus of Highly Dissimilar Finnish Paraphrases (2021) Proceedings for the First Workshop on Modelling Translation: Translatology in the Digital Age Chang Li-Hsin, Pyysalo Sampo, Kanerva Jenna, Ginter Filip
- Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks (2021)
- Natural Language Engineering
- WikiBERT Models: Deep Transfer Learning for Many Languages (2021)
- Linköping Electronic Conference Proceedings
- Assisting nurses in care documentation: from automated sentence classification to coherent document structures with subject headings (2020)
- Journal of Biomedical Semantics
- Classifying online corporate reputation with machine learning: a study in the banking domain (2020)
- Internet Research
- Dependency parsing of biomedical text with BERT (2020)
- BMC Bioinformatics
- Entity-pair embeddings for improving relation extraction in the biomedical domain (2020)
- European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
- Manuscripts, Qualitative Analysis and Features on Vectors: An Attempt for a Synthesis of Conventional and Computational Methods in the Attribution of Late Medieval Anti-Heretical Treatises (2020) Digital Histories. Emergent Approaches within the New Digital History Reima Välimäki, Aleksi Vesanto, Anni Hella, Adam Poznański, Filip Ginter
- Supporting the use of standardized nursing terminologies with automatic subject heading prediction: a comparison of sentence-level text classification methods (2020)
- Journal of the American Medical Informatics Association
- The FISKMO project: Resources and tools for Finnish-Swedish machine translation and cross-linguistic research (2020) Proceedings of the 12th Language Resources and Evaluation Conference Jörg Tiedemann, Tommi Nieminen, Mikko Aulamo, Jenna Kanerva, Akseli Leino, Filip Ginter, Niko Papula
- The reuse of texts in Finnish newspapers and journals, 1771–1920: A digital humanities perspective (2020)
- Historical Methods: A Journal of Quantitative and Interdisciplinary History
- Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task (2020)
- Annual Meeting of the Association for Computational Linguistics
- Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection (2020) Proceedings of the 12th Language Resources and Evaluation Conference Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Jan Hajič, Christopher D. Manning, Sampo Pyysalo, Sebastian Schuster, Francis Tyers, Daniel Zeman
- Is Multilingual BERT Fluent in Language Generation? (2019)
- Linköping Electronic Conference Proceedings