Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,6 @@ language:
|
|
| 10 |
|
| 11 |
# PaddlePaddle/uie-nano
|
| 12 |
|
| 13 |
-
**Try out our space at [https://huggingface.co/spaces/PaddlePaddle/UIE-X](https://huggingface.co/spaces/PaddlePaddle/UIE-X)!**
|
| 14 |
-
|
| 15 |
Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. The unified text-to-structure generation framework, namely UIE, can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism - structural schema instructor, and captures the common IE abilities via a large-scale pre-trained text-to-structure model. Experiments show that UIE achieved the state-of-the-art performance on 4 IE tasks, 13 datasets, and on all supervised, low-resource, and few-shot settings for a wide range of entity, relation, event and sentiment extraction tasks and their unification. These results verified the effectiveness, universality, and transferability of UIE.
|
| 16 |
|
| 17 |
UIE Paper: https://arxiv.org/abs/2203.12277
|
|
@@ -49,15 +47,4 @@ We conducted experiments on the in-house test sets of the three different domain
|
|
| 49 |
|
| 50 |
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).
|
| 51 |
|
| 52 |
-
## Performance on Multimodal Datasets**
|
| 53 |
-
|
| 54 |
-
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:
|
| 55 |
-
|
| 56 |
-
<table>
|
| 57 |
-
<tr><th ><th>General <th>Financial<th colspan='2'>Medical
|
| 58 |
-
<tr><td>🧾🎓<b>uie-x-base (12L768H)</b><td>65.03<td>73.51<td>84.24
|
| 59 |
-
</table>
|
| 60 |
-
|
| 61 |
-
The general test set contains complex samples from different fields and is the most difficult task.
|
| 62 |
-
|
| 63 |
> Detailed Info: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/README_en.md
|
|
|
|
| 10 |
|
| 11 |
# PaddlePaddle/uie-nano
|
| 12 |
|
|
|
|
|
|
|
| 13 |
Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. The unified text-to-structure generation framework, namely UIE, can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism - structural schema instructor, and captures the common IE abilities via a large-scale pre-trained text-to-structure model. Experiments show that UIE achieved the state-of-the-art performance on 4 IE tasks, 13 datasets, and on all supervised, low-resource, and few-shot settings for a wide range of entity, relation, event and sentiment extraction tasks and their unification. These results verified the effectiveness, universality, and transferability of UIE.
|
| 14 |
|
| 15 |
UIE Paper: https://arxiv.org/abs/2203.12277
|
|
|
|
| 47 |
|
| 48 |
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).
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
> Detailed Info: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/README_en.md
|