Hugging Face's logo

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

Token Classification
Transformers
PyTorch
Hindi
xlm-roberta
part-of-speech
Eval Results (legacy)
Model card Files
xet
Community
1

XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Hindi

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-hi")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-hi")
Downloads last month
-
Inference Providers NEW
Token Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

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

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

Evaluation results

  • English Test accuracy on Universal Dependencies v2.8
    self-reported
    75.900
  • Dutch Test accuracy on Universal Dependencies v2.8
    self-reported
    72.300
  • German Test accuracy on Universal Dependencies v2.8
    self-reported
    69.400
  • Italian Test accuracy on Universal Dependencies v2.8
    self-reported
    68.100
  • French Test accuracy on Universal Dependencies v2.8
    self-reported
    67.100
  • Spanish Test accuracy on Universal Dependencies v2.8
    self-reported
    70.200
  • Russian Test accuracy on Universal Dependencies v2.8
    self-reported
    82.900
  • Swedish Test accuracy on Universal Dependencies v2.8
    self-reported
    77.400
  • Norwegian Test accuracy on Universal Dependencies v2.8
    self-reported
    72.400
  • Danish Test accuracy on Universal Dependencies v2.8
    self-reported
    74.900
  • Low Saxon Test accuracy on Universal Dependencies v2.8
    self-reported
    48.000
  • Akkadian Test accuracy on Universal Dependencies v2.8
    self-reported
    21.700
  • Armenian Test accuracy on Universal Dependencies v2.8
    self-reported
    82.100
  • Welsh Test accuracy on Universal Dependencies v2.8
    self-reported
    59.400
  • Old East Slavic Test accuracy on Universal Dependencies v2.8
    self-reported
    63.600
  • Albanian Test accuracy on Universal Dependencies v2.8
    self-reported
    68.500
  • Slovenian Test accuracy on Universal Dependencies v2.8
    self-reported
    71.300
  • Guajajara Test accuracy on Universal Dependencies v2.8
    self-reported
    18.500
  • Kurmanji Test accuracy on Universal Dependencies v2.8
    self-reported
    71.800
  • Turkish Test accuracy on Universal Dependencies v2.8
    self-reported
    75.400