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

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

Downloads last month: 110

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 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-cs

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

Evaluation results

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

83.400
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

83.900
German Test accuracy on Universal Dependencies v2.8
self-reported

83.200
Italian Test accuracy on Universal Dependencies v2.8
self-reported

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

83.500
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

85.900
Russian Test accuracy on Universal Dependencies v2.8
self-reported

91.200
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

88.300
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

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

85.400

View on Papers With Code