diff --git a/spacy/lemmatizer.py b/spacy/lemmatizer.py
index 1738b5e5e..93121a0c5 100644
--- a/spacy/lemmatizer.py
+++ b/spacy/lemmatizer.py
@@ -105,7 +105,6 @@ def lemmatize(string, index, exceptions, rules):
                 oov_forms.append(form)
     # Remove duplicates, and sort forms generated by rules alphabetically.
     forms = list(set(forms))
-    forms.sort()
     # Put exceptions at the front of the list, so they get priority.
     # This is a dodgy heuristic -- but it's the best we can do until we get
     # frequencies on this. We can at least prune out problematic exceptions,
diff --git a/spacy/morphology.pyx b/spacy/morphology.pyx
index da6443b46..bd821d76f 100644
--- a/spacy/morphology.pyx
+++ b/spacy/morphology.pyx
@@ -176,7 +176,7 @@ cdef class Morphology:
         cdef list lemma_strings
         cdef unicode lemma_string
         lemma_strings = self.lemmatizer(py_string, univ_pos, morphology)
-        lemma_string = sorted(lemma_strings)[0]
+        lemma_string = lemma_strings[0]
         lemma = self.strings.add(lemma_string)
         return lemma