Update README.md

Author: spoddutur

README.md

@@ -8,9 +8,17 @@ When Google declared that [The World’s Most Accurate Parser i.e., SyntaxNet go
 <img src="https://github.com/tensorflow/models/blob/master/research/syntaxnet/g3doc/images/looping-parser.gif" width="500" height="300"/>
 
 ## 2. Troubles of the world's best parser SyntaxNet
-Majority of the exmples on its usage are done in 2 ways:
+Predominantly one will find two approaches to use SyntaxNet:
 1. Using (demo.sh)[https://github.com/tensorflow/models/blob/master/research/syntaxnet/syntaxnet/demo.sh] script provided by syntaxnet
-2. Invoke the same from python as a subprocess (which is not a scalable approach).
+2. Invoke the same from python as a subprocess as shown below. This approach is obviously inefficient, non-scalable and over-kill as it internally calls two other python scripts (parser_eval and conll2tree).
+```markdown
+import subprocess
+import os
+os.chdir(r"../models/syntaxnet")
+subprocess.call([ 
+"echo 'Bob brought the pizza to Alice.' | syntaxnet/demo.sh"
+], shell = True)
+```
 ##### I wanted a proper python application where one can do `import syntaxnet` and play with it.
 
 #### 2.1 Pain Part - Syntaxnet is a RESEARCH MODEL: