Update README.md

README.md

@@ -87,7 +87,7 @@ class KeyphraseExtractionPipeline(TokenClassificationPipeline):
     def postprocess(self, model_outputs):
         results = super().postprocess(
             model_outputs=model_outputs,
-            aggregation_strategy=AggregationStrategy.FIRST,
+            aggregation_strategy=AggregationStrategy.SIMPLE,
         )
         return np.unique([result.get("word").strip() for result in results])
 
@@ -118,7 +118,8 @@ the semantic meaning of a text even better than these classical methods.
 Classical methods look at the frequency, occurrence and order of words
 in the text, whereas these neural approaches can capture long-term
 semantic dependencies and context of words in a text.
-""".replace("\n", " ")
+""".replace("
+", " ")
 
 keyphrases = extractor(text)