AndyChiang
commited on
Commit
•
42a5dc6
1
Parent(s):
95b215e
Update README.md
Browse files
README.md
CHANGED
@@ -9,9 +9,39 @@ tags:
|
|
9 |
datasets:
|
10 |
- cloth
|
11 |
widget:
|
12 |
-
- text: "The old man was waiting for a ride across the [MASK] . [SEP] river"
|
13 |
- text: "I feel [MASK] now. [SEP] happy"
|
|
|
14 |
---
|
15 |
|
16 |
# cdgp-csg-bert-cloth
|
17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
datasets:
|
10 |
- cloth
|
11 |
widget:
|
|
|
12 |
- text: "I feel [MASK] now. [SEP] happy"
|
13 |
+
- text: "The old man was waiting for a ride across the [MASK]. [SEP] river"
|
14 |
---
|
15 |
|
16 |
# cdgp-csg-bert-cloth
|
17 |
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
This model is a **Candidate Set Generator** in **"CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model"** at **Findings of EMNLP 2022**.
|
21 |
+
|
22 |
+
Its input are stem and answer, and output is candidate set. It is fine-tuned by [CLOTH](https://github.com/AndyChiangSH/CDGP/blob/main/datasets/CLOTH.zip) dataset based on [bert-base-uncased](https://huggingface.co/bert-base-uncased) model.
|
23 |
+
|
24 |
+
For more details, you can see our paper or [GitHub](https://).
|
25 |
+
|
26 |
+
## How to use?
|
27 |
+
|
28 |
+
|
29 |
+
|
30 |
+
## Dataset
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training
|
35 |
+
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: None
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
## Testing
|
44 |
+
|
45 |
+
## Model list
|
46 |
+
|
47 |
+
## Citation
|