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

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-cy")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-cy")

Downloads last month: 4

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

Evaluation results

English Test accuracy on Universal Dependencies v2.8
self-reported

78.900
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

81.300
German Test accuracy on Universal Dependencies v2.8
self-reported

78.300
Italian Test accuracy on Universal Dependencies v2.8
self-reported

74.900
French Test accuracy on Universal Dependencies v2.8
self-reported

77.100
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

81.000
Russian Test accuracy on Universal Dependencies v2.8
self-reported

82.000
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

80.600