fix_labels

README.md

@@ -26,7 +26,7 @@ The model is based on the [ClinicalBERT - Bio + Discharge Summary BERT Model](ht
 
 You can load the model via the transformers library:
 ```
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline
 tokenizer = AutoTokenizer.from_pretrained("bvanaken/clinical-assertion-negation-bert")
 model = AutoModelForSequenceClassification.from_pretrained("bvanaken/clinical-assertion-negation-bert")
 
@@ -38,11 +38,10 @@ Example input and inference:
 ```
 input = "The patient recovered during the night and now denies any [entity] shortness of breath [entity]."
 
-tokenized_input = tokenizer(input, return_tensors="pt")
-output = model(**tokenized_input)
+classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
 
-import numpy as np
-predicted_label = np.argmax(output.logits.detach().numpy())  ## 1 == ABSENT
+classification = classifier(input)
+# [{'label': 'ABSENT', 'score': 0.9842607378959656}]
 ``` 
 
 ### Cite

config.json

@@ -9,16 +9,16 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "0",
-    "1": "1",
-    "2": "2"
+    "0": "PRESENT",
+    "1": "ABSENT",
+    "2": "POSSIBLE"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "0": 0,
-    "1": 1,
-    "2": 2
+    "PRESENT": 0,
+    "ABSENT": 1,
+    "POSSIBLE": 2
   },
   "language": "english",
   "layer_norm_eps": 1e-12,