Sirvi Autor "Pyysalo, Sampo" järgi

Nüüd näidatakse 1 - 10 10

Fine-grained Named Entity Annotation for Finnish
(Reykjavik, Iceland (Online), Linköping University Electronic Press, Sweden, pp. 135--144, 2021) Luoma, Jouni; Chang, Li-Hsin; Ginter, Filip; Pyysalo, Sampo; Dobnik, Simon; Øvrelid, Lilja
Learning to Extract Biological Event and Relation Graphs
(2009-05-11T08:58:27Z) Björne, Jari; Ginter, Filip; Heimonen, Juho; Pyysalo, Sampo; Salakoski, Tapio
Learning to Extract Biological Event and Relation Graphs
(Odense, Denmark, Northern European Association for Language Technology (NEALT), pp. 18--25, 2009) Björne, Jari; Ginter, Filip; Heimonen, Juho; Pyysalo, Sampo; Salakoski, Tapio; Jokinen, Kristiina; Bick, Eckhard
MULTI-CROSSRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction
(University of Tartu Library, 2023-05) Bassignana, Elisa; Ginter, Filip; Pyysalo, Sampo; Goot, Rob van der; Plank, Barbara
Poro 34B and the Blessing of Multilinguality
(University of Tartu Library, 2025-03) Luukkonen, Risto; Burdge, Jonathan; Zosa, Elaine; Talman, Aarne; Komulainen, Ville; Hatanpää, Väinö; Sarlin, Peter; Pyysalo, Sampo; Johansson, Richard; Stymne, Sara
The pretraining of state-of-the-art large language models now requires trillions of words of text, which is orders of magnitude more than available for the vast majority of languages. While including text in more than one language is an obvious way to acquire more pretraining data, multilinguality is often seen as a curse, and most model training efforts continue to focus near-exclusively on individual large languages. We believe that multilinguality can be a blessing: when the lack of training data is a constraint for effectively training larger models for a target language, augmenting the dataset with other languages can offer a way to improve over the capabilities of monolingual models for that language. In this study, we introduce Poro 34B, a 34 billion parameter model trained for 1 trillion tokens of Finnish, English, and programming languages, and demonstrate that a multilingual training approach can produce a model that substantially advances over the capabilities of existing models for Finnish and excels in translation, while also achieving competitive performance in its class for English and programming languages. We release the model parameters, scripts, and data under open licenses at https://huggingface.co/LumiOpen/Poro-34B.
Toward Multilingual Identification of Online Registers
(Turku, Finland, Linköping University Electronic Press, pp. 292--297, 2019) Laippala, Veronika; Kyllönen, Roosa; Egbert, Jesse; Biber, Douglas; Pyysalo, Sampo; Hartmann, Mareike; Plank, Barbara
Towards the Classification of the Finnish Internet Parsebank: Detecting Translations and Informality
(Vilnius, Lithuania, Linköping University Electronic Press, Sweden, pp. 107--116, 2015) Laippala, Veronika; Kanerva, Jenna; Missilä, Anna; Pyysalo, Sampo; Salakoski, Tapio; Ginter, Filip; Megyesi, Beáta
Toxicity Detection in Finnish Using Machine Translation
(University of Tartu Library, 2023-05) Eskelinen, Anni; Silvala, Laura; Ginter, Filip; Pyysalo, Sampo; Laippala, Veronika
Universal Dependencies for Finnish
(Vilnius, Lithuania, Linköping University Electronic Press, Sweden, pp. 163--172, 2015) Pyysalo, Sampo; Kanerva, Jenna; Missilä, Anna; Laippala, Veronika; Ginter, Filip; Megyesi, Beáta
WikiBERT Models: Deep Transfer Learning for Many Languages
(Reykjavik, Iceland (Online), Linköping University Electronic Press, Sweden, pp. 1–10, 2021) Pyysalo, Sampo; Kanerva, Jenna; Virtanen, Antti; Ginter, Filip; Dobnik, Simon; Øvrelid, Lilja