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

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

Downloads last month: 17

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-mt

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

Evaluation results

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

37.500
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

52.300
German Test accuracy on Universal Dependencies v2.8
self-reported

51.700
Italian Test accuracy on Universal Dependencies v2.8
self-reported

54.700
French Test accuracy on Universal Dependencies v2.8
self-reported

49.100
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

49.500
Russian Test accuracy on Universal Dependencies v2.8
self-reported

64.700
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

52.000
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

48.700
Danish Test accuracy on Universal Dependencies v2.8
self-reported

52.300

View on Papers With Code