metadata

language:
  - lzh
tags:
  - classical chinese
  - literary chinese
  - ancient chinese
  - token-classification
  - pos
license: apache-2.0
pipeline_tag: token-classification
widget:
  - text: 子曰學而時習之不亦説乎有朋自遠方來不亦樂乎人不知而不慍不亦君子乎

roberta-classical-chinese-base-upos

Model Description

This is a RoBERTa model pre-trained on Classical Chinese texts for POS-tagging, derived from roberta-classical-chinese-base-char. Every word is tagged by UPOS (Universal Part-Of-Speech).

How to Use

import torch
from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-classical-chinese-base-upos")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-classical-chinese-base-upos")
s="子曰學而時習之不亦説乎有朋自遠方來不亦樂乎人不知而不慍不亦君子乎"
p=[model.config.id2label[q] for q in torch.argmax(model(tokenizer.encode(s,return_tensors="pt"))[0],dim=2)[0].tolist()[1:-1]]
print(list(zip(s,p)))

Reference

Koichi Yasuoka: Universal Dependencies Treebank of the Four Books in Classical Chinese, DADH2019: 10th International Conference of Digital Archives and Digital Humanities (December 2019), pp.20-28.