Update README.md

Author: zhongkaifu

README.md

@@ -18,7 +18,7 @@ Here is an example of deep bi-directional RNN-CRF network. It contains 3 hidden
 Here is the inner structure of one bi-directional hidden layer.  
 ![](https://github.com/zhongkaifu/RNNSharp/blob/master/RNNSharpLayer.jpg)
 
-Here is the neural network for sequence-to-sequence task. "TokenN" are from source sequence, and "ELayerX-Y" are auto-encoder's hidden layers. Auto-encoder is defined in feature configuration file. "<s>" is always the beginning of target sentence, and "DLayerX-Y" means the decoder's hidden layers. In decoder, it generates one token at one time until "</s>" is generated.  
+Here is the neural network for sequence-to-sequence task. "TokenN" are from source sequence, and "ELayerX-Y" are auto-encoder's hidden layers. Auto-encoder is defined in feature configuration file. &lt;s&gt; is always the beginning of target sentence, and "DLayerX-Y" means the decoder's hidden layers. In decoder, it generates one token at one time until &lt;/s&gt; is generated.  
 ![](https://github.com/zhongkaifu/RNNSharp/blob/master/RNNSharpSeq2Seq.jpg)
 
 ## Supported Feature Types
@@ -47,7 +47,7 @@ U13:C%x[-1,0]/%x[-1,1]
 U14:C%x[0,0]/%x[0,1]  
 U15:C%x[1,0]/%x[1,1]  
 
-The rule-string has two types, one is constant string, and the other is variable. The simplest variable format is {“%x[row,col]”}. Row specifies the offset between current focusing token and generate feature token in row. Col specifies the absolute column position in corpus. Moreover, variable combination is also supported, for example: {“%x[row1, col1]/%x[row2, col2]”}. When we build feature set, variable will be expanded to specific string. Here is an example in training data:  
+The rule-string has two types, one is constant string, and the other is variable. The simplest variable format is {“%x[row,col]”}. Row specifies the offset between current focusing token and generate feature token in row. Col specifies the absolute column position in corpus. Moreover, variable combination is also supported, for example: {“%x[row1, col1]/%x[row2, col2]”}. When we build feature set, variable will be expanded to specific string. Here is an example in training data for named entity task.  
 
 Word       | Pos  | Tag
 -----------|------|----
@@ -204,10 +204,10 @@ your
 name    
 ?       
 
-I
-am
-Zhongkai
-Fu
+I  
+am  
+Zhongkai  
+Fu  
 
 In above example, "What is your name ?" is the source sentence, and "I am Zhongkai Fu" is the target sentence generated by RNNSharp seq-to-seq model. In source sentence, beside word features, any other feautes can be added for it as well such as postag feature in sequence labeling task in above.