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

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

Downloads last month: 12

Safetensors

Model size

277M params

Tensor type

I64

F32

Inference Examples

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-lzh

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

Evaluation results

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

33.600
Dutch Test accuracy on Universal Dependencies v2.8
self-reported

30.900
German Test accuracy on Universal Dependencies v2.8
self-reported

31.100
Italian Test accuracy on Universal Dependencies v2.8
self-reported

31.100
French Test accuracy on Universal Dependencies v2.8
self-reported

30.300
Spanish Test accuracy on Universal Dependencies v2.8
self-reported

30.600
Russian Test accuracy on Universal Dependencies v2.8
self-reported

37.100
Swedish Test accuracy on Universal Dependencies v2.8
self-reported

35.600
Norwegian Test accuracy on Universal Dependencies v2.8
self-reported

32.700
Danish Test accuracy on Universal Dependencies v2.8
self-reported

35.000

View on Papers With Code