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

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

Downloads last month: 4

Safetensors

Model size

277M params

Tensor type

I64

F32

Inference API

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-grc

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

Evaluation results

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

58.300
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

57.100
German Test accuracy on Universal Dependencies v2.8
self-reported

61.300
Italian Test accuracy on Universal Dependencies v2.8
self-reported

56.600
French Test accuracy on Universal Dependencies v2.8
self-reported

57.300
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

54.500
Russian Test accuracy on Universal Dependencies v2.8
self-reported

71.100
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

62.900
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

59.900
Danish Test accuracy on Universal Dependencies v2.8
self-reported

61.600

View on Papers With Code