Identifying closely related languages at sentence level is difficult, in particular because it is often impossible to assign a sentence to a single language. In this paper, we focus on multi-label sentence-level Scandinavian language identification (LID) for Danish, Norwegian Bokmål, Norwegian Nynorsk, and Swedish. We present the Scandinavian Language Identification and Evaluation, SLIDE, a manually curated multi-label evaluation dataset and a suite of LID models with varying speed-accuracy tradeoffs. We demonstrate that the ability to identify multiple languages simultaneously is necessary for any accurate LID method, and present a novel approach to training such multi-label LID models.
View on arXiv@article{fedorova2025_2502.06692,
title={ Multi-label Scandinavian Language Identification (SLIDE) },
author={ Mariia Fedorova and Jonas Sebulon Frydenberg and Victoria Handford and Victoria Ovedie Chruickshank Langø and Solveig Helene Willoch and Marthe Løken Midtgaard and Yves Scherrer and Petter Mæhlum and David Samuel },
journal={arXiv preprint arXiv:2502.06692},
year={ 2025 }
}