Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,8 @@ This model is a fine-tuned version of anferico/bert-for-patents on a unique data
|
|
| 23 |
and 35000 as "Not LS-SYS-related". The fine-tuning is performed on patents' titles and abstracts. The base model was fine-tuned to perform a binary classification task,
|
| 24 |
identifying patents related to the "Learning and Symbolic Systems" domain.
|
| 25 |
|
|
|
|
|
|
|
| 26 |
It achieves the following results on the evaluation set:
|
| 27 |
- Loss: 0.0529
|
| 28 |
- Accuracy: 0.981
|
|
|
|
| 23 |
and 35000 as "Not LS-SYS-related". The fine-tuning is performed on patents' titles and abstracts. The base model was fine-tuned to perform a binary classification task,
|
| 24 |
identifying patents related to the "Learning and Symbolic Systems" domain.
|
| 25 |
|
| 26 |
+
Read the working paper here: https://dipartimenti.unicatt.it/politica-economica-DIPE0050.pdf
|
| 27 |
+
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
- Loss: 0.0529
|
| 30 |
- Accuracy: 0.981
|