Universal-NER commited on
Commit
59b0d5d
1 Parent(s): 333b4ec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -0
README.md CHANGED
@@ -1,3 +1,44 @@
1
  ---
2
  license: cc-by-nc-4.0
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ language:
4
+ - en
5
  ---
6
+
7
+ ---
8
+
9
+
10
+ # UniNER-7B-all
11
+
12
+ **Description**: This model is the best UniNER model. It is trained on the combinations of three data splits: (1) ChatGPT-generated [Pile-NER-type data](https://huggingface.co/datasets/Universal-NER/Pile-NER-type), (2) ChatGPT-generated [Pile-NER-definition data](https://huggingface.co/datasets/Universal-NER/Pile-NER-definition), and (3) 40 supervised datasets in the Universal NER benchmark (see Fig. 4 in paper), where we randomly sample up to 10K instances from the train split of each dataset. Note that CrossNER and MIT datasets are excluded from training for OOD evaluation.
13
+
14
+ Check our [paper](https://arxiv.org/abs/2308.03279) for more information. Check our [repo](https://github.com/universal-ner/universal-ner) about how to use the model.
15
+
16
+ ## Inference
17
+ The template for inference instances is as follows:
18
+ <div style="background-color: #f6f8fa; padding: 20px; border-radius: 10px; border: 1px solid #e1e4e8; box-shadow: 0 2px 5px rgba(0,0,0,0.1);">
19
+ <strong>Prompting template:</strong><br/>
20
+ A virtual assistant answers questions from a user based on the provided text.<br/>
21
+ USER: Text: <span style="color: #d73a49;">{Fill the input text here}</span><br/>
22
+ ASSISTANT: I’ve read this text.<br/>
23
+ USER: What describes <span style="color: #d73a49;">{Fill the entity type here}</span> in the text?<br/>
24
+ ASSISTANT: <span style="color: #0366d6;">(model's predictions in JSON format)</span><br/>
25
+ </div>
26
+
27
+ ### Note: Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
28
+
29
+ ## License
30
+
31
+ This model and its associated data are released under the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) license. They are primarily used for research purposes.
32
+
33
+ ## Citation
34
+
35
+ ```bibtex
36
+ @article{zhou2023universalner,
37
+ title={UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition},
38
+ author={Wenxuan Zhou and Sheng Zhang and Yu Gu and Muhao Chen and Hoifung Poon},
39
+ year={2023},
40
+ eprint={2308.03279},
41
+ archivePrefix={arXiv},
42
+ primaryClass={cs.CL}
43
+ }
44
+ ```