diff --git a/README.md b/README.md
index 65e7029..209586f 100644
--- a/README.md
+++ b/README.md
@@ -20,7 +20,7 @@ To get started, cd into the directory examples/ and run demo.sh. It downloads th
 * sim_sif.py and sim_tfidf.py are for the textual similarity tasks in the paper,
 * supervised_sif_proj.sh is for the supervised tasks in the paper.
 
-Check these files to see the options.
+Check these files to see the options. Make sure you create "log" folder in "example" directory before running above code.
 
 ## Source code
 The code is separated into the following parts:
diff --git a/examples/sif_embedding.py b/examples/sif_embedding.py
old mode 100644
new mode 100755
index 8bafd71..1b65783
--- a/examples/sif_embedding.py
+++ b/examples/sif_embedding.py
@@ -15,7 +15,7 @@
 word2weight = data_io.getWordWeight(weightfile, weightpara) # word2weight['str'] is the weight for the word 'str'
 weight4ind = data_io.getWeight(words, word2weight) # weight4ind[i] is the weight for the i-th word
 # load sentences
-x, m, _ = data_io.sentences2idx(sentences, words) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
+x, m = data_io.sentences2idx(sentences, words) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
 w = data_io.seq2weight(x, m, weight4ind) # get word weights
 
 # set parameters
diff --git a/examples/train.sh b/examples/train.sh
index 9b8746d..c4ed331 100755
--- a/examples/train.sh
+++ b/examples/train.sh
@@ -1,2 +1,2 @@
 cd ../src
-THEANO_FLAGS=mode=FAST_RUN,device=cpu,floatX=float32 python train.py $@
\ No newline at end of file
+THEANO_FLAGS=mode=FAST_RUN,device=cpu,floatX=float32 python2.7 train.py $@
\ No newline at end of file
diff --git a/src/data_io.py b/src/data_io.py
old mode 100644
new mode 100755
index afea0c0..ff4ee15
--- a/src/data_io.py
+++ b/src/data_io.py
@@ -196,6 +196,7 @@ def sentences2idx(sentences, words):
     :param words: a dictionary, words['str'] is the indices of the word 'str'
     :return: x1, m1. x1[i, :] is the word indices in sentence i, m1[i,:] is the mask for sentence i (0 means no word at the location)
     """
+    seq1 = []
     for i in sentences:
         seq1.append(getSeq(i,words))
     x1,m1 = prepare_data(seq1)