Merge pull request #4 from hamelsmu/hamelsmu-patch-1

Update seq2seq_utils.py

Author: Hamel Husain

notebooks/seq2seq_utils.py

@@ -423,7 +423,7 @@ def evaluate_model(self, holdout_bodies, holdout_titles):
         logging.warning('Calculating BLEU.')
 
         #must be careful with nltk api for corpus_bleu!, 
-        # expects List[List[List[str]]] for ground truth, if you forget you will get
-        # errenous results!
+        # expects List[List[List[str]]] for ground truth, using List[List[str]] will give you
+        # erroneous results.
         bleu = corpus_bleu([[a] for a in actual], predicted)
         return bleu