PitchayaS/xlm-roberta-estonian-pos
08
Estonian POS Tagging Model (XLM-RoBERTa-Base)
This model is a fine-tuned version of FacebookAI/xlm-roberta-base for Estonian Part-of-Speech (POS) tagging. It is trained on the Universal Dependencies Treebank (UDT), specifically:
The model provides strong token-level linguistic annotation performance and can be used for downstream Estonian NLP tasks.
Evaluation Results
POS tagging accuracy on UDT test datasets (EDT + EWT): 0.9775