Hugging Face's logo

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

Token Classification
Transformers
PyTorch
Old French (842-ca. 1400)
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 French

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-fro")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-fro")
Downloads last month
14

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

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

Evaluation results

  • English Test accuracy on Universal Dependencies v2.8
    self-reported
    73.400
  • Dutch Test accuracy on Universal Dependencies v2.8
    self-reported
    73.100
  • German Test accuracy on Universal Dependencies v2.8
    self-reported
    70.700
  • Italian Test accuracy on Universal Dependencies v2.8
    self-reported
    72.600
  • French Test accuracy on Universal Dependencies v2.8
    self-reported
    79.300
  • Spanish Test accuracy on Universal Dependencies v2.8
    self-reported
    78.000
  • Russian Test accuracy on Universal Dependencies v2.8
    self-reported
    68.800
  • Swedish Test accuracy on Universal Dependencies v2.8
    self-reported
    76.800
  • Norwegian Test accuracy on Universal Dependencies v2.8
    self-reported
    69.600
  • Danish Test accuracy on Universal Dependencies v2.8
    self-reported
    74.200
View on Papers With Code