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

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

Downloads last month: 13

Inference Examples

Token Classification

Inference API (serverless) is not available, repository is disabled.

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

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

Evaluation results

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

88.400
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

86.900
German Test accuracy on Universal Dependencies v2.8
self-reported

82.700
Italian Test accuracy on Universal Dependencies v2.8
self-reported

84.600
French Test accuracy on Universal Dependencies v2.8
self-reported

83.600
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

83.600
Russian Test accuracy on Universal Dependencies v2.8
self-reported

87.600
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

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

86.400
Danish Test accuracy on Universal Dependencies v2.8
self-reported

89.600

View on Papers With Code