Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ widget:
|
|
| 14 |
<img align="left" src="https://i.ibb.co/p3kQ7Rw/Screenshot-2020-10-06-at-12-16-36-PM.png" width="100"/>
|
| 15 |
|
| 16 |
LEGAL-BERT is a family of BERT models for the legal domain, intended to assist legal NLP research, computational law, and legal technology applications. To pre-train the different variations of LEGAL-BERT, we collected 12 GB of diverse English legal text from several fields (e.g., legislation, court cases, contracts) scraped from publicly available resources. Sub-domain variants (CONTRACTS-, EURLEX-, ECHR-) and/or general LEGAL-BERT perform better than using BERT out of the box for domain-specific tasks. A light-weight model (33% the size of BERT-BASE) pre-trained from scratch on legal data with competitive performance is also available.
|
| 17 |
-
<br/><br
|
| 18 |
|
| 19 |
---
|
| 20 |
|
|
@@ -99,7 +99,6 @@ model = AutoModel.from_pretrained("nlpaueb/legal-bert-base-uncased")
|
|
| 99 |
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('all', '0.08'), ('live', '0.07'), ('certain', '0.07'), ('the', '0.07'), ('farm', '0.05')
|
| 100 |
|
| 101 |
|
| 102 |
-
|
| 103 |
## Evaluation on downstream tasks
|
| 104 |
|
| 105 |
Consider the experiments in the article "LEGAL-BERT: The Muppets straight out of Law School". Chalkidis et al., 2020, (https://aclanthology.org/2020.findings-emnlp.261)
|
| 14 |
<img align="left" src="https://i.ibb.co/p3kQ7Rw/Screenshot-2020-10-06-at-12-16-36-PM.png" width="100"/>
|
| 15 |
|
| 16 |
LEGAL-BERT is a family of BERT models for the legal domain, intended to assist legal NLP research, computational law, and legal technology applications. To pre-train the different variations of LEGAL-BERT, we collected 12 GB of diverse English legal text from several fields (e.g., legislation, court cases, contracts) scraped from publicly available resources. Sub-domain variants (CONTRACTS-, EURLEX-, ECHR-) and/or general LEGAL-BERT perform better than using BERT out of the box for domain-specific tasks. A light-weight model (33% the size of BERT-BASE) pre-trained from scratch on legal data with competitive performance is also available.
|
| 17 |
+
<br/><br/>
|
| 18 |
|
| 19 |
---
|
| 20 |
|
| 99 |
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('all', '0.08'), ('live', '0.07'), ('certain', '0.07'), ('the', '0.07'), ('farm', '0.05')
|
| 100 |
|
| 101 |
|
|
|
|
| 102 |
## Evaluation on downstream tasks
|
| 103 |
|
| 104 |
Consider the experiments in the article "LEGAL-BERT: The Muppets straight out of Law School". Chalkidis et al., 2020, (https://aclanthology.org/2020.findings-emnlp.261)
|