---
title: csc
canonical_url: "https://www.modelscope.cn/datasets/Weaxrcks/csc"
md_url: "https://www.modelscope.cn/datasets/Weaxrcks/csc.md"
repository: Weaxrcks/csc
chinese_name: "中文文本纠错数据集"
last_updated: 2024-01-02
license: "Apache License 2.0"
storage_size: "815 MB"
downloads: 890
stars: 9
---

# csc

> csc - Weaxrcks 在 ModelScope 开源的数据集。中文文本拼写+语法纠错。包含120W+样例，收集自NLPCC、CGED、ECSpell、SIGHAN等等。

Weaxrcks/csc 是 ModelScope 魔搭社区上的数据集，存储大小 815 MB，采用 Apache License 2.0 许可。

- **Repository**: Weaxrcks/csc
- **License**: Apache License 2.0
- **Storage size**: 815 MB
- **Downloads**: 890
- **Stars**: 9
- **Last updated**: 2024-01-02

Source: https://www.modelscope.cn/datasets/Weaxrcks/csc

---

# Dataset for CSC

中文纠错数据集

# Dataset Description

Chinese Spelling Correction (CSC) is a task to detect and correct misspelled characters in Chinese texts.

共计 120w 条数据，以下是数据来源


| 数据集                         | 语料                         | 链接                                                                                                                                                                                            |
| ---
---
---
---
---
---
---
---
---
---
 | ---
---
---
---
---
---
---
---
---
- | ---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
---
-- |
| SIGHAN+Wang271K 拼写纠错数据集 | SIGHAN+Wang271K(27万条)      | https://huggingface.co/datasets/shibing624/CSC                                                                                                                                                  |
| ECSpell 拼写纠错数据集         | 包含法律、医疗、金融等领域   | https://github.com/Aopolin-Lv/ECSpell                                                                                                                                                           |
| CGED 语法纠错数据集            | 仅包含了2016和2021年的数据集 | https://github.com/wdimmy/Automatic-Corpus-Generation?spm=a2c22.12282016.0.0.5f3e7398w7SL4P                                                                                                     |
| NLPCC 纠错数据集               | 包含语法纠错和拼写纠错       | https://github.com/Arvid-pku/NLPCC2023_Shared_Task8<br/>http://tcci.ccf.org.cn/conference/2023/dldoc/nacgec_training.zip<br/>http://tcci.ccf.org.cn/conference/2018/dldoc/trainingdata02.tar.gz |
| pycorrector 语法纠错集         | 中文语法纠错数据集           | https://github.com/shibing624/pycorrector/tree/master/examples/data/grammar                                                                                                                     |

其余的数据集还可以看

- 中文文本纠错数据集汇总 (天池)：https://tianchi.aliyun.com/dataset/138195
- NLPCC 2023中文语法纠错数据集：http://tcci.ccf.org.cn/conference/2023/taskdata.php

# Languages

The data in CSC are in Chinese.

# Dataset Structure

An example of "train" looks as follows:

```json
{
  "conversations": [
    {"from":"human","value":"对这个句子纠错\n\n以后，我一直以来自学汉语了。"},
    {"from":"gpt","value":"从此以后，我就一直自学汉语了。"}
  ]
}
```