liamcripwell commited on
Commit
3922f1b
1 Parent(s): 9179c2c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -0
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # CTRL44 Classification model
2
+
3
+ This is a pretrained version of the 4-class simplification operation classifier presented in the NAACL 2022 paper "Controllable Sentence Simplification via Operation Classification". It was trained on the IRSD classification dataset.
4
+
5
+ Predictions from this model can be used for input into the [simplification model](https://huggingface.co/liamcripwell/ctrl44-simp) to reproduce pipeline results seen in the paper.
6
+
7
+ ## How to use
8
+
9
+ Here is how to use this model in PyTorch:
10
+
11
+ ```python
12
+ from transformers import RobertaForSequenceClassification, AutoTokenizer
13
+
14
+ model = RobertaForSequenceClassification.from_pretrained("liamcripwell/ctrl44-clf")
15
+ tokenizer = AutoTokenizer.from_pretrained("liamcripwell/ctrl44-clf")
16
+
17
+ text = "Barack Hussein Obama II is an American politician who served as the 44th president of the United States from 2009 to 2017."
18
+ inputs = tokenizer(text, return_tensors="pt")
19
+
20
+ with torch.no_grad():
21
+ logits = model(**inputs).logits
22
+ predicted_class_id = logits.argmax().item()
23
+ predicted_class_name = model.config.id2label[predicted_class_id]
24
+ ```