#natural language process...
Mar 2026
CWoMP: Morpheme Representation Learning for Interlinear Glossing
This work proposes CWoMP (Contrastive Word-Morpheme Pretraining), which instead treats morphemes as atomic form-meaning units with learned representations with particularly strong gains in extremely low-resource settings.
Morris Alper, Enora Rice, Bhargav Shandilya et al.
· arXiv.org · 0 citations