Reworked the sentence to make the reference clear (#2570)

I thought I committed this change to the last PR, but it didn't go through.

README.md

@@ -48,11 +48,10 @@ framework and deploying to a variety of hardware targets. We strongly believe in
 providing freedom, performance, and ease-of-use to AI developers. 
 
 The diagram below shows deep learning frameworks and hardware targets
-supported by nGraph. The Intel® Nervana™ Neural Network Processor (Intel® Nervana™ NNP-L 
-for Learning and the NNP-I for Inference) refer to Intel's next generation deep 
-learning accelators for training and inference respectively. Future plans 
-for supporting addtional deep learning frameworks and backends are outlined in
-the [ecosystem] section. 
+supported by nGraph. NNP-L and NNP-I in the diagram refer to Intel's next generation
+deep learning accelators: Intel® Nervana™ Neural Network Processor for Learning and 
+Inference. Future plans for supporting addtional deep learning frameworks
+and backends are outlined in the [ecosystem] section. 
 
 
 ![](doc/sphinx/source/graphics/main_diagram_fw_hw.png)