diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4582d7ca57..cc3f7581c3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@ Changes
 * Implemented LsiModel.docs_processed attribute
 * Added LdaMallet support. Added LdaVowpalWabbit, LdaMallet example to notebook. Added test suite for coherencemodel and aggregation.
   Added `topics` parameter to coherencemodel. Can now provide tokenized topics to calculate coherence value (@dsquareindia, #750)
+* Changed `use_lowercase` option in word2vec accuracy to `case_insensitive` to account for case variations in training vocabulary (@jayantj, #714)
 
 0.13.1, 2016-06-22
 
diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
index 7d56a79a15..223487413b 100644
--- a/gensim/models/word2vec.py
+++ b/gensim/models/word2vec.py
@@ -1573,13 +1573,15 @@ def accuracy(self, questions, restrict_vocab=30000, most_similar=most_similar, c
         The accuracy is reported (=printed to log and returned as a list) for each
         section separately, plus there's one aggregate summary at the end.
 
-        `restrict_vocab` is an optional integer which limits the vocab to be used
-        for answering questions. For example, restrict_vocab=10000 would only check
-        the first 10000 word vectors in the vocabulary order. (This may be meaningful
-        if you've sorted the vocabulary by descending frequency.)
-
-        Use `case_insensitive` to convert all words in questions and vocab to their uppercase form before evaluating
-        the accuracy. Useful in case of case-mismatch between training tokens and question words.  (default True).
+        Use `restrict_vocab` to ignore all questions containing a word not in the first `restrict_vocab`
+        words (default top 30,000). This may be meaningful if you've sorted the vocabulary by descending 
+        frequency. In case `case_insensitive` is True, the first `restrict_vocab` words are taken first, and then 
+        case normalization is performed.
+
+        Use `case_insensitive` to convert all words in questions and vocab to their uppercase form before 
+        evaluating the accuracy (default True). Useful in case of case-mismatch between training tokens 
+        and question words. In case of multiple case variants of a single word, the vector for the first
+        occurrence (also the most frequent if vocabulary is sorted) is taken.
 
         This method corresponds to the `compute-accuracy` script of the original C word2vec.