Commit
•
2448da8
1
Parent(s):
5f98890
Update README.md
Browse files
README.md
CHANGED
@@ -10,6 +10,11 @@ model-index:
|
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
|
|
|
|
|
|
|
13 |
```python
|
14 |
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
15 |
import torch
|
@@ -54,4 +59,13 @@ for prefix in ["Person", "Location", "John Smith births in", "Positive opinion"]
|
|
54 |
predictions = [prediction for prediction in predictions if is_sublst(words, prediction.split())]
|
55 |
|
56 |
print(prefix, predictions)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
```
|
|
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# MetaIE
|
15 |
+
|
16 |
+
This a meta-model distilled from ChatGPT-3.5-turbo for information extraction. This is an intermediate checkpoint that can be well-transferred to all kinds of downstream information extraction tasks. This model can also be tested by different label-to-span matching as shown in the following example:
|
17 |
+
|
18 |
```python
|
19 |
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
20 |
import torch
|
|
|
59 |
predictions = [prediction for prediction in predictions if is_sublst(words, prediction.split())]
|
60 |
|
61 |
print(prefix, predictions)
|
62 |
+
```
|
63 |
+
|
64 |
+
The output will be
|
65 |
+
|
66 |
+
```python
|
67 |
+
"Person" ['John Smith']
|
68 |
+
"Location" ['Los Angeles']
|
69 |
+
"John Smith births in" ['Los Angeles']
|
70 |
+
"Positive opinion" ['loves his hometown']
|
71 |
```
|