Minor fixes to nuget README.md file (microsoft#49)

Author: jignparm

docs/CSharp_API.md

@@ -2,14 +2,14 @@
 The ONNX runtime provides a C# .Net binding for running inference on ONNX models in any of the .Net standard platforms. The API is .Net standard 1.1 compliant for maximum portability. This document describes the API. 
 
 ## NuGet Package
-There is a NuGet package Microsoft.ML.OnnxRuntime available for .Net consumers, which includes the prebuilt binaries for ONNX runtime.  The API is portable across all platforms and architectures supported by the .Net standard, although currently the NuGet package contains the prebuilt binaries for Windows 10 platform on x64 CPUs only.
+The Microsoft.ML.OnnxRuntime Nuget package includes the precompiled binaries for ONNX runtime, and includes libraries for Windows 10 platform and X64 CPUs. The APIs conform to .Net Standard 1.1.
 
 ## Getting Started
-Here is simple tutorial for getting started with running inference on an existing ONNX model for a given input data (a.k.a query). Say the model is trained using any of the well-known training frameworks and exported as an ONNX model into a file named `model.onnx`. The runtime incarnation of a model is an `InferenceSession` object. You simply construct an `InferenceSession` object using the model file as parameter --
+Here is simple tutorial for getting started with running inference on an existing ONNX model for a given input data. The model is typically trained using any of the well-known training frameworks and exported into the ONNX format. To start scoring using the model, open a session using the `InferenceSession` class, passing in the file path to the model as a parameter.
 
     var session = new InferenceSession("model.onnx");
 
-Once a session is created, you can run queries on the session using your input data, using the `Run` method of the  `InferenceSession`. Both input and output of `Run` method are represented as collections of .Net `Tensor` objects (as defined in [System.Numerics.Tensor](https://www.nuget.org/packages/System.Numerics.Tensors)) -
+Once a session is created, you can execute queries using the `Run` method of the  `InferenceSession` object. Currently, only `Tensor` type of input and outputs  are supported. The results of the `Run` method are represented as a collection of .Net `Tensor` objects (as defined in [System.Numerics.Tensor](https://www.nuget.org/packages/System.Numerics.Tensors)).
 
     Tensor<float> t1, t2;  // let's say data is fed into the Tensor objects
     var inputs = new List<NamedOnnxValue>()
@@ -19,7 +19,8 @@ Once a session is created, you can run queries on the session using your input d
                  };
     IReadOnlyCollection<NamedOnnxValue> results = session.Run(inputs);
 
-You can load your input data into Tensor<T> objects in several ways. A simple example is to create the Tensor from arrays -
+You can load your input data into Tensor<T> objects in several ways. A simple example is to create the Tensor from arrays.
+
     float[] sourceData;  // assume your data is loaded into a flat float array
     int[] dimensions;    // and the dimensions of the input is stored here
     Tensor<float> t1 = new DenseTensor<float>(sourceData, dimensions);    
@@ -84,7 +85,7 @@ Accessor to the default static option object
 
 #### Methods
     AppendExecutionProvider(ExecutionProvider provider);
-Appends execution provider to the session. For any operator in the graph the first execution provider that implements the operator will be user. ExecutionProvider is defined as the following enum -
+Appends execution provider to the session. For any operator in the graph the first execution provider that implements the operator will be user. ExecutionProvider is defined as the following enum.
 
     enum ExecutionProvider
     {
@@ -112,4 +113,3 @@ The type of Exception that is thrown in most of the error conditions related to
 
 
 
-