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

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

Downloads last month: 3

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-la

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

Evaluation results

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

81.500
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

79.600
German Test accuracy on Universal Dependencies v2.8
self-reported

78.200
Italian Test accuracy on Universal Dependencies v2.8
self-reported

78.000
French Test accuracy on Universal Dependencies v2.8
self-reported

78.100
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

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

89.800
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

86.000
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

81.500
Danish Test accuracy on Universal Dependencies v2.8
self-reported

85.700

View on Papers With Code