Hugging Face's logo

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

Token Classification
Transformers
PyTorch
Slovenian
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: Slovenian

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-sl")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-sl")
Downloads last month
4

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

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

Evaluation results

  • English Test accuracy on Universal Dependencies v2.8
    self-reported
    81.700
  • Dutch Test accuracy on Universal Dependencies v2.8
    self-reported
    83.100
  • German Test accuracy on Universal Dependencies v2.8
    self-reported
    81.200
  • Italian Test accuracy on Universal Dependencies v2.8
    self-reported
    81.300
  • French Test accuracy on Universal Dependencies v2.8
    self-reported
    79.900
  • Spanish Test accuracy on Universal Dependencies v2.8
    self-reported
    84.900
  • Russian Test accuracy on Universal Dependencies v2.8
    self-reported
    91.500
  • Swedish Test accuracy on Universal Dependencies v2.8
    self-reported
    86.000
  • Norwegian Test accuracy on Universal Dependencies v2.8
    self-reported
    78.400
  • Danish Test accuracy on Universal Dependencies v2.8
    self-reported
    83.700
View on Papers With Code