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

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

Downloads last month: 2

Inference Providers NEW

Token Classification

This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

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

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

Evaluation results

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

47.900
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

50.200
German Test accuracy on Universal Dependencies v2.8
self-reported

38.900
Italian Test accuracy on Universal Dependencies v2.8
self-reported

46.800
French Test accuracy on Universal Dependencies v2.8
self-reported

50.200
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

51.300
Russian Test accuracy on Universal Dependencies v2.8
self-reported

52.400
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

51.500
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

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

50.800

View on Papers With Code