diff --git a/README.md b/README.md
index ee6423b06f8017a4f9b8884152200dd9457e1c12..1659159cccfa87e80e2fbfd736d2739e309ad1d2 100644
--- a/README.md
+++ b/README.md
@@ -63,8 +63,8 @@ Dive into Deep Learning with PyTorch code.
 [6.6 通过时间反向传播](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.6_bptt.md)     
 [6.7 门控循环单元（GRU）](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.7_gru.md)              
 [6.8 长短期记忆（LSTM）](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.8_lstm.md)      
-[6.9 深度循环神经网络¶](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.9_deep-rnn.md)              
-[6.10 双向循环神经网络¶](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.10_bi-rnn.md)  
+[6.9 深度循环神经网络](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.9_deep-rnn.md)              
+[6.10 双向循环神经网络](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.10_bi-rnn.md)   
  
 
 
diff --git a/docs/chapter06_RNN/6.10_bi-rnn.md b/docs/chapter06_RNN/6.10_bi-rnn.md
index 3ad21e4126583a740d48e622f794bcadc3930a5f..fe68fc8023ece7297f0a4367acc0169c1fb1b26c 100644
--- a/docs/chapter06_RNN/6.10_bi-rnn.md
+++ b/docs/chapter06_RNN/6.10_bi-rnn.md
@@ -3,8 +3,7 @@
 之前介绍的循环神经网络模型都是假设当前时间步是由前面的较早时间步的序列决定的，因此它们都将信息通过隐藏状态从前往后传递。有时候，当前时间步也可能由后面时间步决定。例如，当我们写下一个句子时，可能会根据句子后面的词来修改句子前面的用词。双向循环神经网络通过增加从后往前传递信息的隐藏层来更灵活地处理这类信息。图6.12演示了一个含单隐藏层的双向循环神经网络的架构。
 
 <div align=center>
-<img width="300" src="../../img/chapter06/6.10_birnn.svg
-"/>
+<img width="300" src="../../img/chapter06/6.10_birnn.svg"/>
 </div>
 <div align=center>图6.12 双向循环神经网络的架构</div>