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

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

Downloads last month: 12

Safetensors

Model size

277M params

Tensor type

I64

F32

Inference Providers NEW

Token Classification

This model is not currently available via any of the supported Inference Providers.

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

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

Evaluation results

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

87.100
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

87.500
German Test accuracy on Universal Dependencies v2.8
self-reported

80.500
Italian Test accuracy on Universal Dependencies v2.8
self-reported

88.700
French Test accuracy on Universal Dependencies v2.8
self-reported

89.700
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

91.800
Russian Test accuracy on Universal Dependencies v2.8
self-reported

88.600
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

87.700
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

82.500
Danish Test accuracy on Universal Dependencies v2.8
self-reported

88.600

View on Papers With Code