Roberta Classical Chinese Large Sentence Segmentation

🚀 roberta-classical-chinese-large-sentence-segmentation

This is a RoBERTa model designed for sentence segmentation of Classical Chinese texts. It offers a solution for accurately segmenting sentences in Classical Chinese, leveraging pre - trained knowledge from a base model.

🚀 Quick Start

This RoBERTa model is pre - trained on Classical Chinese texts for sentence segmentation. It is derived from roberta-classical-chinese-large-char. Every segmented sentence begins with token - class "B" and ends with token - class "E" (except for single - character sentence with token - class "S").

✨ Features

• Language and Tags: Supports languages related to classical Chinese, with tags including "classical chinese", "literary chinese", "ancient chinese", "sentence segmentation", and "token - classification".
• Base Model: Built upon the KoichiYasuoka/roberta-classical-chinese-large-char base model.
• License: Licensed under the "apache - 2.0" license.
• Pipeline Tag: It belongs to the "token - classification" pipeline.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-sentence-segmentation")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-sentence-segmentation")
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"))["logits"],dim=2)[0].tolist()[1:-1]]
print("".join(c+"。" if q=="E" or q=="S" else c for c,q in zip(s,p)))

📚 Documentation

Reference

Koichi Yasuoka: Sentence Segmentation of Classical Chinese Texts Using Transformers and BERT/RoBERTa Models, IPSJ Symposium Series, Vol.2021, No.1 (December 2021), pp.104 - 109.

📄 License

This project is licensed under the "apache - 2.0" license.