Hugging Face's logo

wietsedv
/
xlm-roberta-base-ft-udpos28-orv

Token Classification
Transformers
PyTorch
Old Russian
xlm-roberta
part-of-speech
Eval Results
Inference Endpoints
Model card Files Community
Edit model card

XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Old East Slavic

This model is part of our paper called:

  • Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages

Check the Space for more details.

Usage 

from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-orv")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-orv")
Downloads last month
8

Dataset used to train wietsedv/xlm-roberta-base-ft-udpos28-orv

Space using wietsedv/xlm-roberta-base-ft-udpos28-orv 1

Evaluation results

  • English Test accuracy on Universal Dependencies v2.8
    self-reported
    79.400
  • Dutch Test accuracy on Universal Dependencies v2.8
    self-reported
    77.800
  • German Test accuracy on Universal Dependencies v2.8
    self-reported
    79.300
  • Italian Test accuracy on Universal Dependencies v2.8
    self-reported
    77.500
  • French Test accuracy on Universal Dependencies v2.8
    self-reported
    75.200
  • Spanish Test accuracy on Universal Dependencies v2.8
    self-reported
    77.200
  • Russian Test accuracy on Universal Dependencies v2.8
    self-reported
    87.900
  • Swedish Test accuracy on Universal Dependencies v2.8
    self-reported
    83.000
  • Norwegian Test accuracy on Universal Dependencies v2.8
    self-reported
    78.600
  • Danish Test accuracy on Universal Dependencies v2.8
    self-reported
    82.900
View on Papers With Code