small edits and comments

app.py

@@ -21,8 +21,8 @@ st.subheader("Analysing challenging domains with only a handful of examples")
 
 st.write(f"""This space uses models based on [XLNet](https://huggingface.co/xlnet-base-cased) to identify medical entities in a text.
 The following is a random sentence from [bigbio/biored](https://huggingface.co/datasets/bigbio/biored).
-It was tagged by a model which was trained on 200 examples from the original dataset.
-It is very possible that there should be some mistakes.
+It was tagged by a model which was trained on just 200 examples from the original dataset.
+It is very possible that there are some mistakes.
 """)
 
 txt = sentences[session_state.counter]

helpers.py

@@ -11,14 +11,21 @@ def annotate_sentence(sentence, predictions):
     output = []
     i = 0
     for p in predictions:
+        # Add initial tokens
         if sentence[i:p['start']] != '':
             output.append(sentence[i:p['start']])
-        output.append(
-            (sentence[p['start']:p['end']], p['entity_group'], colors[p['entity_group']])
-            if p['entity_group'] != 'null'
-            else sentence[p['start']:p['end']]
-            )
+
+        # Add prediction tokens
+        if sentence[p['start']:p['end']] != '':
+            output.append(
+                (sentence[p['start']:p['end']], p['entity_group'], colors[p['entity_group']])
+                if p['entity_group'] != 'null'
+                else sentence[p['start']:p['end']]
+                )
+
         i = p['end']
+    
+    # Add any trailing tokens
     if sentence[i:] != '':
         output.append(sentence[p['end']:])
     return output