NorEventGen: generative event extraction from Norwegian news

Huiling You, Samia Touileb, Erik Velldal, Lilja Øvrelid


Abstract
In this work, we approach event extraction from Norwegian news text using a generation-based approach which formulates the task as text-to-structure generation. We present experiments assessing the effect of different modeling configurations and provide an analysis of the model predictions and typical system errors. Finally, we apply our system to a large corpus of raw news texts and analyze the resulting distribution of event structures in a fairly representative snap-shot of the Norwegian news landscape.
Anthology ID:
2025.nodalida-1.79
Volume:
Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
Month:
march
Year:
2025
Address:
Tallinn, Estonia
Editors:
Richard Johansson, Sara Stymne
Venue:
NoDaLiDa
SIG:
Publisher:
University of Tartu Library
Note:
Pages:
801–811
Language:
URL:
https://preview.aclanthology.org/fix-sig-urls/2025.nodalida-1.79/
DOI:
Bibkey:
Cite (ACL):
Huiling You, Samia Touileb, Erik Velldal, and Lilja Øvrelid. 2025. NorEventGen: generative event extraction from Norwegian news. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 801–811, Tallinn, Estonia. University of Tartu Library.
Cite (Informal):
NorEventGen: generative event extraction from Norwegian news (You et al., NoDaLiDa 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-sig-urls/2025.nodalida-1.79.pdf