diff --git a/README.md b/README.md
index 55e8271e5c0aab0ff80c49dfa4749b417de57488..b36b039052165371586ff3dd2b3c283f2c08751a 100644
--- a/README.md
+++ b/README.md
@@ -49,7 +49,7 @@ See [Installation Guide](http://paddlepaddle.org/doc/build/) to install from pre
## Documentation
- [Chinese Documentation](http://paddlepaddle.org/doc_cn/)
-- [Quick Start](http://paddlepaddle.org/doc/demo/quick_start/)
+- [Quick Start](http://paddlepaddle.org/doc/demo/quick_start/index_en)
You can follow the quick start tutorial to learn how use PaddlePaddle
step-by-step.
diff --git a/doc/demo/quick_start/index_en.md b/doc/demo/quick_start/index_en.md
index e0f819283f4d2bee816dc6711b059e51e3234f05..41ee3d1abbc96e300b96643e1defbbff16a3d9f4 100644
--- a/doc/demo/quick_start/index_en.md
+++ b/doc/demo/quick_start/index_en.md
@@ -395,7 +395,7 @@ paddle train \
--use_gpu=false
```
-If you want to install the remote training platform, which enables distributed training on clusters, follow the instructions here: Platform documentation. We do not provide examples on how to train on clusters. Please refer to other demos or platform training documentation for mode details on training on clusters.
+If you want to install the remote training platform, which enables distributed training on clusters, follow the instructions here: Platform documentation. We do not provide examples on how to train on clusters. Please refer to other demos or platform training documentation for mode details on training on clusters.
## Inference
You can use the trained model to perform prediction on the dataset with no labels. You can also evaluate the model on dataset with labels to obtain its test accuracy.