Update README.md
Browse files
README.md
CHANGED
|
@@ -4,30 +4,3 @@ datasets:
|
|
| 4 |
- cuad
|
| 5 |
---
|
| 6 |
|
| 7 |
-
# Finetuned legal contract review QA model based 👩⚖️ 📑
|
| 8 |
-
|
| 9 |
-
Best model presented in the master thesis [*Exploring CUAD using RoBERTa span-selection QA models for legal contract review*](https://github.com/gustavhartz/transformers-legal-tasks) for QA on the Contract Understanding Atticus Dataset. Full training logic and associated thesis available through link.
|
| 10 |
-
|
| 11 |
-
Outperform the most popular HF cuad model [Rakib/roberta-base-on-cuad](https://huggingface.co/Rakib/roberta-base-on-cuad) and is the best model for CUAD on Hugging Face 26/06/2022
|
| 12 |
-
|
| 13 |
-
| **Model name** | **Top 1 Has Ans F1** | **Top 3 Has Ans F1** |
|
| 14 |
-
|-----------------------------------------|----------------------|----------------------|
|
| 15 |
-
| gustavhartz/roberta-base-cuad-finetuned | 85.68 | 94.06 |
|
| 16 |
-
| Rakib/roberta-base-on-cuad | 81.26 | 92.48 |
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
For questions etc. go through the Github repo :)
|
| 20 |
-
|
| 21 |
-
### Citation
|
| 22 |
-
|
| 23 |
-
If you found the code of thesis helpful you can please cite it :)
|
| 24 |
-
```
|
| 25 |
-
@thesis{ha2022,
|
| 26 |
-
author = {Hartz, Gustav Selfort},
|
| 27 |
-
title = {Exploring CUAD using RoBERTa span-selection QA models for legal contract review},
|
| 28 |
-
language = {English},
|
| 29 |
-
format = {thesis},
|
| 30 |
-
year = {2022},
|
| 31 |
-
publisher = {DTU Department of Applied Mathematics and Computer Science}
|
| 32 |
-
}
|
| 33 |
-
```
|
|
|
|
| 4 |
- cuad
|
| 5 |
---
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|