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

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

Downloads last month: 108

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-pl

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

Evaluation results

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

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

78.300
German Test accuracy on Universal Dependencies v2.8
self-reported

77.700
Italian Test accuracy on Universal Dependencies v2.8
self-reported

77.500
French Test accuracy on Universal Dependencies v2.8
self-reported

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

81.700
Russian Test accuracy on Universal Dependencies v2.8
self-reported

90.600
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

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

78.900
Danish Test accuracy on Universal Dependencies v2.8
self-reported

83.300

View on Papers With Code