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: 9

Inference Examples

Token Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

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