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

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

Downloads last month: 14

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

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

Evaluation results

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

89.900
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

90.000
German Test accuracy on Universal Dependencies v2.8
self-reported

88.800
Italian Test accuracy on Universal Dependencies v2.8
self-reported

89.400
French Test accuracy on Universal Dependencies v2.8
self-reported

89.000
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

91.600
Russian Test accuracy on Universal Dependencies v2.8
self-reported

90.300
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

92.400
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

87.300
Danish Test accuracy on Universal Dependencies v2.8
self-reported

98.300

View on Papers With Code