Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
tags:
|
| 4 |
+
- Spanish
|
| 5 |
+
- BART
|
| 6 |
+
- Legal
|
| 7 |
+
|
| 8 |
+
datasets:
|
| 9 |
+
- Spanish-legal-corpora
|
| 10 |
+
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
## BART Legal Spanish ⚖️
|
| 14 |
+
|
| 15 |
+
**BART Legal** (base) is an BART-like model trained on [A collection of corpora of Spanish legal domain](https://zenodo.org/record/5495529#.YZItp3vMLJw).
|
| 16 |
+
|
| 17 |
+
BART is a transformer encoder-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function and (2) learning a model to reconstruct the original text.
|
| 18 |
+
|
| 19 |
+
This model is particularly effective when fine-tuned for text generation tasks (e.g., summarization, translation) but also works well for comprehension tasks (e.g., text classification, question answering).
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
## Training details
|
| 24 |
+
|
| 25 |
+
TBA
|
| 26 |
+
|
| 27 |
+
## Model details ⚙
|
| 28 |
+
|
| 29 |
+
TBA
|
| 30 |
+
|
| 31 |
+
## Evaluation metrics (for discriminator) 🧾
|
| 32 |
+
|
| 33 |
+
|Metric | # Score |
|
| 34 |
+
|-------|---------|
|
| 35 |
+
|Accuracy| 0.955|
|
| 36 |
+
|Precision| 0.790|
|
| 37 |
+
|AUC | 0.971|
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Benchmarks 🔨
|
| 41 |
+
|
| 42 |
+
WIP 🚧
|
| 43 |
+
|
| 44 |
+
## How to use with `transformers`
|
| 45 |
+
|
| 46 |
+
TBA
|
| 47 |
+
|
| 48 |
+
## Acknowledgments
|
| 49 |
+
|
| 50 |
+
TBA
|
| 51 |
+
|
| 52 |
+
## Citation
|
| 53 |
+
If you want to cite this model, you can use this:
|
| 54 |
+
|
| 55 |
+
```bibtex
|
| 56 |
+
@misc {manuel_romero_2023,
|
| 57 |
+
author = { {Manuel Romero} },
|
| 58 |
+
title = { bart-legal-base-es (Revision 27bc9e1) },
|
| 59 |
+
year = 2023,
|
| 60 |
+
url = { https://huggingface.co/mrm8488/bart-legal-base-es },
|
| 61 |
+
doi = { 10.57967/hf/0467 },
|
| 62 |
+
publisher = { Hugging Face }
|
| 63 |
+
}
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488)
|
| 68 |
+
|
| 69 |
+
> Made with <span style="color: #e25555;">♥</span> in Spain
|