Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ widget:
|
|
| 11 |
ITALIAN-LEGAL-BERT is based on <a href="https://huggingface.co/dbmdz/bert-base-italian-xxl-cased">bert-base-italian-xxl-cased</a> with additional pre-training of the Italian BERT model on Italian civil law corpora.
|
| 12 |
It achieves better results than the ‘general-purpose’ Italian BERT in different domain-specific tasks.
|
| 13 |
|
|
|
|
|
|
|
| 14 |
<h2>Training procedure</h2>
|
| 15 |
We initialized ITALIAN-LEGAL-BERT with ITALIAN XXL BERT
|
| 16 |
and pretrained for an additional 4 epochs on 3.7 GB of preprocessed text from the National Jurisprudential
|
|
|
|
| 11 |
ITALIAN-LEGAL-BERT is based on <a href="https://huggingface.co/dbmdz/bert-base-italian-xxl-cased">bert-base-italian-xxl-cased</a> with additional pre-training of the Italian BERT model on Italian civil law corpora.
|
| 12 |
It achieves better results than the ‘general-purpose’ Italian BERT in different domain-specific tasks.
|
| 13 |
|
| 14 |
+
<a href="https://huggingface.co/dlicari/Italian-Legal-BERT-SC">HERE</a>, It is the ITALIAN-LEGAL-BERT variant pre-trained from scratch on Italian legal documents (<a href="https://huggingface.co/dlicari/Italian-Legal-BERT-SC">ITA-LEGAL-BERT-SC</a>) based on the CamemBERT architecture
|
| 15 |
+
|
| 16 |
<h2>Training procedure</h2>
|
| 17 |
We initialized ITALIAN-LEGAL-BERT with ITALIAN XXL BERT
|
| 18 |
and pretrained for an additional 4 epochs on 3.7 GB of preprocessed text from the National Jurisprudential
|