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

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

Downloads last month: 16

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

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

Evaluation results

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

73.900
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

69.800
German Test accuracy on Universal Dependencies v2.8
self-reported

69.900
Italian Test accuracy on Universal Dependencies v2.8
self-reported

73.200
French Test accuracy on Universal Dependencies v2.8
self-reported

69.000
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

65.600
Russian Test accuracy on Universal Dependencies v2.8
self-reported

82.900
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

79.800
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

75.100
Danish Test accuracy on Universal Dependencies v2.8
self-reported

79.100

View on Papers With Code