addressed all comments by Ines

spacy/lang/en/stop_words.py

@@ -69,7 +69,10 @@ yet you your yours yourself yourselves
 """.split()
 )
 
-for hyphen in ["'", "`", "‘", "´", "’"]:
+contractions = ["n't", "'d", "'ll", "'m", "'re", "'s", "'ve"]
-    for stopword in u"n't 'd 'll 'm 're 's 've".split():
+STOP_WORDS.update(contractions)
-        STOP_WORDS.add(stopword.replace("'", hyphen))
+
+for apostrophe in ["‘", "’"]:
+    for stopword in contractions:
+        STOP_WORDS.add(stopword.replace("'", apostrophe))
 

spacy/tests/regression/test_issue3449.py

@@ -1,4 +1,6 @@
 # coding: utf8
+from __future__ import unicode_literals
+
 import pytest
 
 from spacy.lang.en import English

spacy/tests/regression/test_issue3521.py

@@ -1,14 +1,16 @@
 # coding: utf8
+from __future__ import unicode_literals
+
 import pytest
 
 
 @pytest.mark.parametrize(
     "word",
     [
-        u"don't",
+        "don't",
-        u"don’t",
+        "don’t",
-        u"I'd",
+        "I'd",
-        u"I’d",
+        "I’d",
     ],
 )
 def test_issue3521(en_tokenizer, word):