Update README.md

README.md

@@ -12,10 +12,13 @@ This model is a finetuned RoBERTa-based model pre-trained from scratch on Dutch
 ## Minimal example
 
 ```python
-tokenizer = AutoTokenizer.from_pretrained("UMCU/MedRoBERTa.nl_NegationDetection")
-model = AutoModelForTokenClassification.from_pretrained("UMCU/MedRoBERTa.nl_NegationDetection")
+tokenizer = AutoTokenizer\
+             .from_pretrained("UMCU/MedRoBERTa.nl_NegationDetection")
+model = AutoModelForTokenClassification\
+            .from_pretrained("UMCU/MedRoBERTa.nl_NegationDetection")
 
-some_text = "De patient was niet aanspreekbaar en hij zag er grauw uit. Hij heeft de inspanningstest echter goed doorstaan." 
+some_text = "De patient was niet aanspreekbaar en hij zag er grauw uit. \
+Hij heeft de inspanningstest echter goed doorstaan." 
 inputs = tokenizer(some_text, return_tensors='pt')
 output = model.forward(inputs)
 probas = torch.nn.functional.softmax(output.logits[0]).detach().numpy()
@@ -31,7 +34,7 @@ results = [{'token': input_tokens[idx],
 
 ```
 
-It perhaps good to note that we assume the [Inside-Outside-Beginning](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)) format.
+It is perhaps good to note that we assume the [Inside-Outside-Beginning](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)) format.
 
 ## Intended use
 The model is finetuned for negation detection on Dutch clinical text. Since it is a domain-specific model trained on medical data, it is meant to be used on medical NLP tasks for Dutch. This particular model is trained on a 512-max token windows surrounding the concept-to-be negated.