Abstract
We study highly granular dialect identification on Limburgish, a non-standardized, low-resource language. Additionally, we present some new results related to dialect normalization and phonological dialect translation to decrease the barriers associated with non-standardized NLP. We make use of the Woordenboek van de Limburgse Dialecten (“Dictionary of the Limburgish Dialects”), a geotagged dialectological dataset with many potential uses within NLP. Our results are consistent with notions and maps in traditional Limburgish dialectology.
How to Cite:
Simons, A., De Pascale, S. & Franco, K., (2024) “Kunstmatige intelligentie voor het Limburgs: nieuwe tools en inzichten uit oude data”, Janeway JS 78, 157–187.
Rights: @ the author(s)
Downloads:
Downloads are not available for this article.
4 Views