Update README.md
Browse files
README.md
CHANGED
|
@@ -46,15 +46,4 @@ We conducted experiments on the in-house test sets of the three different domain
|
|
| 46 |
|
| 47 |
0-shot means that no training data is directly used for prediction through paddlenlp.Taskflow, and 5-shot means that each category contains 5 pieces of labeled data for model fine-tuning. Experiments show that UIE can further improve the performance with a small amount of data (few-shot).
|
| 48 |
|
| 49 |
-
## Performance on Multimodal Datasets**
|
| 50 |
-
|
| 51 |
-
We experimented on the zero-shot performance of UIE-X on the in-house multi-modal test sets in three different domains of general, financial, and medical:
|
| 52 |
-
|
| 53 |
-
<table>
|
| 54 |
-
<tr><th ><th>General <th>Financial<th colspan='2'>Medical
|
| 55 |
-
<tr><td>🧾🎓<b>uie-x-base (12L768H)</b><td>65.03<td>73.51<td>84.24
|
| 56 |
-
</table>
|
| 57 |
-
|
| 58 |
-
The general test set contains complex samples from different fields and is the most difficult task.
|
| 59 |
-
|
| 60 |
> Detailed Info: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/README_en.md
|
|
|
|
| 46 |
|
| 47 |
0-shot means that no training data is directly used for prediction through paddlenlp.Taskflow, and 5-shot means that each category contains 5 pieces of labeled data for model fine-tuning. Experiments show that UIE can further improve the performance with a small amount of data (few-shot).
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
> Detailed Info: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/README_en.md
|