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

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

Downloads last month: 11

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-ar

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

Evaluation results

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

62.800
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

63.500
German Test accuracy on Universal Dependencies v2.8
self-reported

63.800
Italian Test accuracy on Universal Dependencies v2.8
self-reported

60.200
French Test accuracy on Universal Dependencies v2.8
self-reported

58.500
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

64.900
Russian Test accuracy on Universal Dependencies v2.8
self-reported

77.200
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

68.500
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

64.600
Danish Test accuracy on Universal Dependencies v2.8
self-reported

66.100

View on Papers With Code