diff --git a/fluid/neural_machine_translation/transformer/model.py b/fluid/neural_machine_translation/transformer/model.py
index ee2d1d501f25881e401bb725b67b0a78b71f7605..4468f47915078d639a9ae5de3a07515faf4d1079 100644
--- a/fluid/neural_machine_translation/transformer/model.py
+++ b/fluid/neural_machine_translation/transformer/model.py
@@ -219,6 +219,7 @@ def prepare_encoder_decoder(src_word,
         size=[src_max_len, src_emb_dim],
         param_attr=fluid.ParamAttr(
             name=pos_enc_param_name, trainable=False))
+    src_pos_enc.stop_gradient = True
     enc_input = src_word_emb + src_pos_enc
     return layers.dropout(
         enc_input,