Update README.md
Browse files
README.md
CHANGED
@@ -1,18 +1,26 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
---
|
4 |
-
|
5 |
-
This repository contains the checkpoint for the corruptor of LIFE, which is trained with gold evidence. Please refer to the code of LIFE at https://github.com/NLPCode/LIFE for more details.
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
---
|
4 |
+
|
5 |
+
This repository contains the checkpoint for the corruptor of LIFE, which is trained with gold evidence. Please refer to the code of LIFE at https://github.com/NLPCode/LIFE for more details.
|
6 |
+
## Usage
|
7 |
+
```
|
8 |
+
# Load the model
|
9 |
+
from transformers import AutoConfig, AutoModelForSeq2SeqLM, AutoTokenizer
|
10 |
+
tokenizer = AutoTokenizer.from_pretrained("He-Xingwei/LIFE-Corruptor-GE")
|
11 |
+
model = AutoModelForSeq2SeqLM.from_pretrained("He-Xingwei/LIFE-Corruptor-GE")
|
12 |
+
```
|
13 |
+
|
14 |
+
## Citation
|
15 |
+
If you want to use this model in your research, please cite our [paper](https://ojs.aaai.org/index.php/AAAI/article/view/29778/):
|
16 |
+
```bash
|
17 |
+
|
18 |
+
@inproceedings{he2024improving,
|
19 |
+
title={Improving Factual Error Correction by Learning to Inject Factual Errors},
|
20 |
+
author={He, Xingwei and Zhang, Qianru and Jin, A-Long and Ma, Jun and Yuan, Yuan and Yiu, Siu Ming},
|
21 |
+
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
22 |
+
volume={38},
|
23 |
+
number={16},
|
24 |
+
pages={18197--18205},
|
25 |
+
year={2024}
|
26 |
}
|