XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Croatian
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-hr")
model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-hr")
- Downloads last month
- 4
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-hr
Space using wietsedv/xlm-roberta-base-ft-udpos28-hr 1
Evaluation results
- English Test accuracy on Universal Dependencies v2.8self-reported83.700
- Dutch Test accuracy on Universal Dependencies v2.8self-reported83.700
- German Test accuracy on Universal Dependencies v2.8self-reported83.200
- Italian Test accuracy on Universal Dependencies v2.8self-reported83.200
- French Test accuracy on Universal Dependencies v2.8self-reported84.200
- Spanish Test accuracy on Universal Dependencies v2.8self-reported87.800
- Russian Test accuracy on Universal Dependencies v2.8self-reported91.400
- Swedish Test accuracy on Universal Dependencies v2.8self-reported85.400
- Norwegian Test accuracy on Universal Dependencies v2.8self-reported79.000
- Danish Test accuracy on Universal Dependencies v2.8self-reported83.800