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

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

Downloads last month: 3

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

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

Evaluation results

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

68.100
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

64.000
German Test accuracy on Universal Dependencies v2.8
self-reported

65.800
Italian Test accuracy on Universal Dependencies v2.8
self-reported

61.200
French Test accuracy on Universal Dependencies v2.8
self-reported

56.900
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

59.500
Russian Test accuracy on Universal Dependencies v2.8
self-reported

74.300
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

69.100
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

64.800
Danish Test accuracy on Universal Dependencies v2.8
self-reported

70.000

View on Papers With Code