Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages
Barend Beekhuizen · 2025
This paper introduces VORM, an unsupervised morphological segmentation system, leveraging translation data to infer highly accurate morphological transformations, including lessfrequently modeled processes such as infixation and reduplication.The system is evaluated on standard benchmark data and a novel, typologically diverse, dataset of 37 languages.Model performance is competitive and sometimes superior on canonical segmentation, but more limited on surface segmentation.