|
--- |
|
license: apache-2.0 |
|
language: |
|
- zh |
|
library_name: transformers |
|
tags: |
|
- Roberta |
|
- Chinese Pre-trained Language Model |
|
--- |
|
|
|
Please use 'XLMRoberta' related functions to load this model! |
|
|
|
# MigBERT | 中文混合粒度预训练模型 |
|
[Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models](https://arxiv.org/abs/2303.10893) |
|
|
|
# Demo | 使用样例 |
|
https://github.com/xnliang98/MigBERT |
|
|
|
# Citation |
|
如果你觉得我们的工作对你有用，请在您的工作中引用我们的文章。 |
|
|
|
If you find our resource or paper is useful, please consider including the following citation in your paper. |
|
|
|
``` |
|
@misc{liang2023character, |
|
title={Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models}, |
|
author={Xinnian Liang and Zefan Zhou and Hui Huang and Shuangzhi Wu and Tong Xiao and Muyun Yang and Zhoujun Li and Chao Bian}, |
|
year={2023}, |
|
eprint={2303.10893}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CL} |
|
} |
|
``` |
