Update README.md

README.md

@@ -16,7 +16,11 @@ Sample usage:
 ```python
 from transformers import pipeline
 
-oracle = pipeline('ner', model='dicta-il/dictabert-ner')
+oracle = pipeline('ner', model='dicta-il/dictabert-ner', aggregation_strategy='simple')
+
+# if we set aggregation_strategy to simple, we need to define a decoder for the tokenizer. Note that the last wordpiece of a group will still be emitted
+from tokenizers.decoders import WordPiece
+oracle.tokenizer.backend_tokenizer.decoder = WordPiece()
 
 sentence = 'הכי דרמטי שיש: שער של סדריק המחליף העניק לזיו אריה ניצחון שני בשלושה משחקים ועלייה מעל הקו האדום.'
 oracle(sentence)
@@ -26,28 +30,25 @@ Output:
 ```json
 [
   {
-    "entity": "B-PER",
-    "score": "0.99827814",
-    "index": 7,
+    "entity_group": "PER",
+    "score": "0.99978834",
     "word": "סדריק",
-    "start": 22,
-    "end": 27
+    "start": "22",
+    "end": "27"
   },
   {
-    "entity": "B-PER",
-    "score": "0.9995943",
-    "index": 10,
+    "entity_group": "PER",
+    "score": "0.99994457",
     "word": "לזי",
-    "start": 41,
-    "end": 44
+    "start": "41",
+    "end": "44"
   },
   {
-    "entity": "I-PER",
-    "score": "0.9995154",
-    "index": 12,
+    "entity_group": "PER",
+    "score": "0.99993944",
     "word": "אריה",
-    "start": 46,
-    "end": 50
+    "start": "46",
+    "end": "50"
   }
 ]
 ```